var bibbase_data = {"data":"\"Loading..\"\n\n
\n\n \n\n \n\n \n \n\n \n\n \n \n\n \n\n \n
\n generated by\n \n \"bibbase.org\"\n\n \n
\n \n\n
\n\n \n\n\n
\n\n Excellent! Next you can\n create a new website with this list, or\n embed it in an existing web page by copying & pasting\n any of the following snippets.\n\n
\n JavaScript\n (easiest)\n
\n \n <script src=\"https://bibbase.org/show?bib=https%3A%2F%2Fclulab.github.io%2Fclulab_publications.bib&fullnames=1&jsonp=1&jsonp=1\"></script>\n \n
\n\n PHP\n
\n \n <?php\n $contents = file_get_contents(\"https://bibbase.org/show?bib=https%3A%2F%2Fclulab.github.io%2Fclulab_publications.bib&fullnames=1&jsonp=1\");\n print_r($contents);\n ?>\n \n
\n\n iFrame\n (not recommended)\n
\n \n <iframe src=\"https://bibbase.org/show?bib=https%3A%2F%2Fclulab.github.io%2Fclulab_publications.bib&fullnames=1&jsonp=1\"></iframe>\n \n
\n\n

\n For more details see the documention.\n

\n
\n
\n\n
\n\n This is a preview! To use this list on your own web site\n or create a new web site from it,\n create a free account. The file will be added\n and you will be able to edit it in the File Manager.\n We will show you instructions once you've created your account.\n
\n\n
\n\n

To the site owner:

\n\n

Action required! Mendeley is changing its\n API. In order to keep using Mendeley with BibBase past April\n 14th, you need to:\n

    \n
  1. renew the authorization for BibBase on Mendeley, and
    2. \n
  2. update the BibBase URL\n in your page the same way you did when you initially set up\n this page.\n
    3. \n
\n

\n\n

\n \n \n Fix it now\n

\n
\n\n
\n\n\n
\n \n \n
\n
\n  \n 2025\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing.\n \n \n \n \n\n\n \n Vlad Negru; Robert Vacareanu; Camelia Lemnaru; Mihai Surdeanu; and Rodica Potolea.\n\n\n \n\n\n\n In Findings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025. \n \n\n\n\n
\n\n\n\n \n \n \"MorphNLI:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{negru-et-al-naacl2025-morphnli,\n    title = "MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing",\n    author = "Vlad Negru and Robert Vacareanu and Camelia Lemnaru and Mihai Surdeanu and Rodica Potolea",\n    booktitle = "Findings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)",\n    year = "2025",\n    url = "https://arxiv.org/abs/2502.09567",\n    abstract = "We introduce MorphNLI, a modular step-by-step approach to natural language inference (NLI). When classifying the premise-hypothesis pairs into {entailment, contradiction, neutral}, we use a language model to generate the necessary edits to incrementally transform (i.e., morph) the premise into the hypothesis. Then, using an off-the-shelf NLI model we track how the entailment progresses with these atomic changes, aggregating these intermediate labels into a final output. We demonstrate the advantages of our proposed method particularly in realistic cross-domain settings, where our method always outperforms strong baselines with improvements up to 12.6% (relative). Further, our proposed approach is explainable as the atomic edits can be used to understand the overall NLI label.",\n}\n\n
\n
\n\n\n
\n We introduce MorphNLI, a modular step-by-step approach to natural language inference (NLI). When classifying the premise-hypothesis pairs into entailment, contradiction, neutral, we use a language model to generate the necessary edits to incrementally transform (i.e., morph) the premise into the hypothesis. Then, using an off-the-shelf NLI model we track how the entailment progresses with these atomic changes, aggregating these intermediate labels into a final output. We demonstrate the advantages of our proposed method particularly in realistic cross-domain settings, where our method always outperforms strong baselines with improvements up to 12.6% (relative). Further, our proposed approach is explainable as the atomic edits can be used to understand the overall NLI label.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2024\n \n \n (29)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Context.\n \n \n \n \n\n\n \n Enrique Noriega-Atala; Robert Vacareanu; Salena Torres Ashton; Adarsh Pyarelal; Clayton T Morrison; and Mihai Surdeanu.\n\n\n \n\n\n\n In Yaser Al-Onaizan; Mohit Bansal; and Yun-Nung Chen., editor(s), Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3821–3829, Miami, Florida, USA, November 2024. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"WhenPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{noriega-atala-etal-2024-happen,\n    title = "When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Context",\n    author = "Noriega-Atala, Enrique  and\n      Vacareanu, Robert  and\n      Ashton, Salena Torres  and\n      Pyarelal, Adarsh  and\n      Morrison, Clayton T  and\n      Surdeanu, Mihai",\n    editor = "Al-Onaizan, Yaser  and\n      Bansal, Mohit  and\n      Chen, Yun-Nung",\n    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",\n    month = nov,\n    year = "2024",\n    address = "Miami, Florida, USA",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.findings-emnlp.219/",\n    doi = "10.18653/v1/2024.findings-emnlp.219",\n    pages = "3821--3829",\n    abstract = "We introduce a neural architecture finetuned for the task of scenario context generation: The relevant location and time of an event or entity mentioned in text. Contextualizing information extraction helps to scope the validity of automated finings when aggregating them as knowledge graphs. Our approach uses a high-quality curated dataset of time and location annotations in a corpus of epidemiology papers to train an encoder-decoder architecture. We also explored the use of data augmentation techniques during training. Our findings suggest that a relatively small fine-tuned encoder-decoder model performs better than out-of-the-box LLMs and semantic role labeling parsers to accurate predict the relevant scenario information of a particular entity or event."\n}\n\n
\n
\n\n\n
\n We introduce a neural architecture finetuned for the task of scenario context generation: The relevant location and time of an event or entity mentioned in text. Contextualizing information extraction helps to scope the validity of automated finings when aggregating them as knowledge graphs. Our approach uses a high-quality curated dataset of time and location annotations in a corpus of epidemiology papers to train an encoder-decoder architecture. We also explored the use of data augmentation techniques during training. Our findings suggest that a relatively small fine-tuned encoder-decoder model performs better than out-of-the-box LLMs and semantic role labeling parsers to accurate predict the relevant scenario information of a particular entity or event.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization.\n \n \n \n \n\n\n \n Portia Cooper; Harshita Narnoli; and Mihai Surdeanu.\n\n\n \n\n\n\n 2024.\n \n\n\n\n
\n\n\n\n \n \n \"FindingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@misc{cooper2024findingwolfsheepsclothing,\n      title={Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization}, \n      author={Portia Cooper and Harshita Narnoli and Mihai Surdeanu},\n      year={2024},\n      eprint={2412.12212},\n      archivePrefix={arXiv},\n      primaryClass={cs.CR},\n      url={https://arxiv.org/abs/2412.12212}, \n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Classify First, and Then Extract: Prompt Chaining Technique for Information Extraction.\n \n \n \n \n\n\n \n Alice Kwak; Clayton Morrison; Derek Bambauer; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Natural Legal Language Processing Workshop 2024, November 2024. \n \n\n\n\n
\n\n\n\n \n \n \"ClassifyPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{kwak-et-al-nllp2024-error-analysis,\n    title = "Classify First, and Then Extract: Prompt Chaining Technique for Information Extraction",\n    author = "Alice Kwak and Clayton Morrison and Derek Bambauer and Mihai Surdeanu",\n    booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2024",\n    month = nov,\n    year = "2024",\n    url = "https://clulab.org/papers/nllp2024_kwak-et-al.pdf",\n    abstract = "This work presents a new task-aware prompt design and example retrieval approach for information extraction (IE) using a prompt chaining technique. Our approach divides IE tasks into two steps: (1) text classification to understand what information (e.g., entity or event types) is contained in the underlying text and (2) information extraction for the identified types. Initially, we use a large language model (LLM) in a few-shot setting to classify the contained information. The classification output is used to select the relevant prompt and retrieve the examples relevant to the input text. Finally, we ask a LLM to do the information extraction with the generated prompt. By evaluating our approach on legal IE tasks with two different LLMs, we demonstrate that the prompt chaining technique improves the LLM’s overall performance in a few-shot setting when compared to the baseline in which examples from all possible classes are included in the prompt. Our approach can be used in a low-resource setting as it does not require a large amount of training data. Also, it can be easily adapted to many different IE tasks by simply adjusting the prompts. Lastly, it provides a cost benefit by reducing the number of tokens in the prompt.",\n}\n\n
\n
\n\n\n
\n This work presents a new task-aware prompt design and example retrieval approach for information extraction (IE) using a prompt chaining technique. Our approach divides IE tasks into two steps: (1) text classification to understand what information (e.g., entity or event types) is contained in the underlying text and (2) information extraction for the identified types. Initially, we use a large language model (LLM) in a few-shot setting to classify the contained information. The classification output is used to select the relevant prompt and retrieve the examples relevant to the input text. Finally, we ask a LLM to do the information extraction with the generated prompt. By evaluating our approach on legal IE tasks with two different LLMs, we demonstrate that the prompt chaining technique improves the LLM’s overall performance in a few-shot setting when compared to the baseline in which examples from all possible classes are included in the prompt. Our approach can be used in a low-resource setting as it does not require a large amount of training data. Also, it can be easily adapted to many different IE tasks by simply adjusting the prompts. Lastly, it provides a cost benefit by reducing the number of tokens in the prompt.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Learning to Generate Rules for Realistic Few-Shot Relation Classification: An Encoder-Decoder Approach.\n \n \n \n\n\n \n Mayank Singh; and Eduardo Blanco.\n\n\n \n\n\n\n In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, USA and virtual meeting, November 2024. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{singh-2024-learning,\n    title = "Learning to Generate Rules for Realistic Few-Shot Relation Classification: An Encoder-Decoder Approach",\n    author = "Singh, Mayank and Blanco, Eduardo",\n    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",\n    month = nov,\n    year = "2024",\n    address = "Miami, USA and virtual meeting",\n    publisher = "Association for Computational Linguistics",\n    abstract = "We propose a neuro-symbolic approach for realistic few-shot relation classification via rules. Instead of building neural models to predict relations, we design them to output straightforward rules that can be used to extract relations. The rules are generated using custom T5-style Encoder-Decoder Language Models. Crucially, our rules are fully interpretable and pliable (i.e., humans can easily modify them to boost performance). Through a combination of rules generated by these models along with a very effective, novel baseline, we demonstrate a few-shot relation-classification performance that is comparable to or stronger than the state of the art on the Few-Shot TACRED and NYT29 benchmarks while increasing interpretability and maintaining pliability.",\n}\n\n
\n
\n\n\n
\n We propose a neuro-symbolic approach for realistic few-shot relation classification via rules. Instead of building neural models to predict relations, we design them to output straightforward rules that can be used to extract relations. The rules are generated using custom T5-style Encoder-Decoder Language Models. Crucially, our rules are fully interpretable and pliable (i.e., humans can easily modify them to boost performance). Through a combination of rules generated by these models along with a very effective, novel baseline, we demonstrate a few-shot relation-classification performance that is comparable to or stronger than the state of the art on the Few-Shot TACRED and NYT29 benchmarks while increasing interpretability and maintaining pliability.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Paraphrasing in Affirmative Terms Improves Negation Understanding.\n \n \n \n \n\n\n \n MohammadHossein Rezaei; and Eduardo Blanco.\n\n\n \n\n\n\n In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Bangkok, Thailand, August 2024. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ParaphrasingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{rezaei-blanco-2024-paraphrasing,\n  author    = {Rezaei, MohammadHossein  and  Blanco, Eduardo},\n  title     = {Paraphrasing in Affirmative Terms Improves Negation Understanding},\n  booktitle      = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},\n  month          = {August},\n  year           = {2024},\n  address        = {Bangkok, Thailand},\n  publisher      = {Association for Computational Linguistics},\n  pages     = {},\n  abstract  = {Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless strategies that incorporate affirmative interpretations (i.e., paraphrases without negation) to make models more robust against negation. Crucially, our affirmative interpretations are obtained automatically. We show improvements with CondaQA, a large corpus requiring reasoning with negation, and five natural language understanding tasks.},\n  url       = {https://arxiv.org/pdf/2406.07492}\n}\n\n
\n
\n\n\n
\n Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless strategies that incorporate affirmative interpretations (i.e., paraphrases without negation) to make models more robust against negation. Crucially, our affirmative interpretations are obtained automatically. We show improvements with CondaQA, a large corpus requiring reasoning with negation, and five natural language understanding tasks.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n MARiA at SemEval 2024 Task-6: Hallucination Detection Through LLMs, MNLI, and Cosine similarity.\n \n \n \n \n\n\n \n Reza Sanayei; Abhyuday Singh; Mohammadhossein Rezaei; and Steven Bethard.\n\n\n \n\n\n\n In Atul Kr. Ojha; A. Seza Doğruöz; Harish Tayyar Madabushi; Giovanni Da San Martino; Sara Rosenthal; and Aiala Rosá., editor(s), Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1584–1588, Mexico City, Mexico, June 2024. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"MARiAPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{sanayei-etal-2024-maria,\n    title = "{MAR}i{A} at {S}em{E}val 2024 Task-6: Hallucination Detection Through {LLM}s, {MNLI}, and Cosine similarity",\n    author = "Sanayei, Reza  and\n      Singh, Abhyuday  and\n      Rezaei, Mohammadhossein  and\n      Bethard, Steven",\n    editor = {Ojha, Atul Kr.  and\n      Do{\\u{g}}ru{\\"o}z, A. Seza  and\n      Tayyar Madabushi, Harish  and\n      Da San Martino, Giovanni  and\n      Rosenthal, Sara  and\n      Ros{\\'a}, Aiala},\n    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.semeval-1.225",\n    pages = "1584--1588",\n    abstract = "The advent of large language models (LLMs) has revolutionized Natural Language Generation (NLG), offering unmatched text generation capabilities. However, this progress introduces significant challenges, notably hallucinations{---}semantically incorrect yet fluent outputs. This phenomenon undermines content reliability, as traditional detection systems focus more on fluency than accuracy, posing a risk of misinformation spread.Our study addresses these issues by proposing a unified strategy for detecting hallucinations in neural model-generated text, focusing on the SHROOM task in SemEval 2024. We employ diverse methodologies to identify output divergence from the source content. We utilized Sentence Transformers to measure cosine similarity between source-hypothesis and source-target embeddings, experimented with omitting source content in the cosine similarity computations, and Leveragied LLMs{'} In-Context Learning with detailed task prompts as our methodologies. The varying performance of our different approaches across the subtasks underscores the complexity of Natural Language Understanding tasks, highlighting the importance of addressing the nuances of semantic correctness in the era of advanced language models.",\n}\n\n
\n
\n\n\n
\n The advent of large language models (LLMs) has revolutionized Natural Language Generation (NLG), offering unmatched text generation capabilities. However, this progress introduces significant challenges, notably hallucinations—semantically incorrect yet fluent outputs. This phenomenon undermines content reliability, as traditional detection systems focus more on fluency than accuracy, posing a risk of misinformation spread.Our study addresses these issues by proposing a unified strategy for detecting hallucinations in neural model-generated text, focusing on the SHROOM task in SemEval 2024. We employ diverse methodologies to identify output divergence from the source content. We utilized Sentence Transformers to measure cosine similarity between source-hypothesis and source-target embeddings, experimented with omitting source content in the cosine similarity computations, and Leveragied LLMs' In-Context Learning with detailed task prompts as our methodologies. The varying performance of our different approaches across the subtasks underscores the complexity of Natural Language Understanding tasks, highlighting the importance of addressing the nuances of semantic correctness in the era of advanced language models.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n CLULab-UofA at SemEval-2024 Task 8: Detecting Machine-Generated Text Using Triplet-Loss-Trained Text Similarity and Text Classification.\n \n \n \n \n\n\n \n Mohammadhossein Rezaei; Yeaeun Kwon; Reza Sanayei; Abhyuday Singh; and Steven Bethard.\n\n\n \n\n\n\n In Atul Kr. Ojha; A. Seza Doğruöz; Harish Tayyar Madabushi; Giovanni Da San Martino; Sara Rosenthal; and Aiala Rosá., editor(s), Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1498–1504, Mexico City, Mexico, June 2024. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"CLULab-UofAPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{rezaei-etal-2024-clulab,\n    title = "{CLUL}ab-{U}of{A} at {S}em{E}val-2024 Task 8: Detecting Machine-Generated Text Using Triplet-Loss-Trained Text Similarity and Text Classification",\n    author = "Rezaei, Mohammadhossein  and\n      Kwon, Yeaeun  and\n      Sanayei, Reza  and\n      Singh, Abhyuday  and\n      Bethard, Steven",\n    editor = {Ojha, Atul Kr.  and\n      Do{\\u{g}}ru{\\"o}z, A. Seza  and\n      Tayyar Madabushi, Harish  and\n      Da San Martino, Giovanni  and\n      Rosenthal, Sara  and\n      Ros{\\'a}, Aiala},\n    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.semeval-1.215",\n    pages = "1498--1504",\n    abstract = "Detecting machine-generated text is a critical task in the era of large language models. In this paper, we present our systems for SemEval-2024 Task 8, which focuses on multi-class classification to discern between human-written and maching-generated texts by five state-of-the-art large language models. We propose three different systems: unsupervised text similarity, triplet-loss-trained text similarity, and text classification. We show that the triplet-loss trained text similarity system outperforms the other systems, achieving 80{\\%} accuracy on the test set and surpassing the baseline model for this subtask. Additionally, our text classification system, which takes into account sentence paraphrases generated by the candidate models, also outperforms the unsupervised text similarity system, achieving 74{\\%} accuracy.",\n}\n\n
\n
\n\n\n
\n Detecting machine-generated text is a critical task in the era of large language models. In this paper, we present our systems for SemEval-2024 Task 8, which focuses on multi-class classification to discern between human-written and maching-generated texts by five state-of-the-art large language models. We propose three different systems: unsupervised text similarity, triplet-loss-trained text similarity, and text classification. We show that the triplet-loss trained text similarity system outperforms the other systems, achieving 80% accuracy on the test set and surpassing the baseline model for this subtask. Additionally, our text classification system, which takes into account sentence paraphrases generated by the candidate models, also outperforms the unsupervised text similarity system, achieving 74% accuracy.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Retrieval Augmented Generation of Subjective Explanations for Socioeconomic Scenarios.\n \n \n \n \n\n\n \n Razvan-Gabriel Dumitru; Maria Alexeeva; Keith Alcock; Nargiza Ludgate; Cheonkam Jeong; Zara Fatima Abdurahaman; Prateek Puri; Brian Kirchhoff; Santadarshan Sadhu; and Mihai Surdeanu.\n\n\n \n\n\n\n In Sixth Workshop on NLP and Computational Social Science (at NAACL) 2024, 2024. \n \n\n\n\n
\n\n\n\n \n \n \"RetrievalPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{\n  dumitru2024retrieval,\n  title={Retrieval Augmented Generation of Subjective Explanations for Socioeconomic Scenarios},\n  author={Dumitru, Razvan-Gabriel and Alexeeva, Maria and Alcock, Keith and Ludgate, Nargiza and Jeong, Cheonkam and Abdurahaman, Zara Fatima and Puri, Prateek and Kirchhoff, Brian and Sadhu, Santadarshan and Surdeanu, Mihai},\n  booktitle={Sixth Workshop on  NLP and Computational Social Science (at NAACL) 2024},\n  year={2024},\n  url={http://clulab.org/papers/naacl-css2024-rag.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n General Purpose Verification for Chain of Thought Prompting.\n \n \n \n \n\n\n \n Robert Vacareanu; Anurag Pratik; Evangelia Spiliopoulou; Zheng Qi; Giovanni Paolini; Neha Anna John; Jie Ma; Yassine Benajiba; and Miguel Ballesteros.\n\n\n \n\n\n\n ArXiv, abs/2405.00204. 2024.\n \n\n\n\n
\n\n\n\n \n \n \"GeneralPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Vacareanu2024GeneralVerificationLLM,\n  title={General Purpose Verification for Chain of Thought Prompting},\n  author={Robert Vacareanu and Anurag Pratik and Evangelia Spiliopoulou and Zheng Qi and Giovanni Paolini and Neha Anna John and Jie Ma and Yassine Benajiba and Miguel Ballesteros},\n  journal={ArXiv},\n  year={2024},\n  volume={abs/2405.00204},\n  url={https://arxiv.org/pdf/2405.00204.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples.\n \n \n \n \n\n\n \n Robert Vacareanu; Vlad-Andrei Negru; Vasile Suciu; and Mihai Surdeanu.\n\n\n \n\n\n\n ArXiv, abs/2404.07544. 2024.\n \n\n\n\n
\n\n\n\n \n \n \"FromPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 7 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Vacareanu2024LLMsRegression,\n  title={From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples},\n  author={Robert Vacareanu and Vlad-Andrei Negru and Vasile Suciu and Mihai Surdeanu},\n  journal={ArXiv},\n  year={2024},\n  volume={abs/2404.07544},\n  url={https://arxiv.org/pdf/2404.07544.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification.\n \n \n \n \n\n\n \n Robert Vacareanu; Fahmida Alam; Md Asiful Islam; Haris Riaz; and Mihai Surdeanu.\n\n\n \n\n\n\n In Findings of the Association for Computational Linguistics: NAACL 2024, Mexico City, Mexico, June 2024. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"BestPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 25 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{vacareanu2024softrules,\n    title = "Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification",\n    author = "Robert Vacareanu and Fahmida Alam and Md Asiful Islam and Haris Riaz and Mihai Surdeanu",\n    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics",\n    url = "https://arxiv.org/pdf/2403.03305.pdf",\n    abstract = "This paper introduces a novel neuro-symbolic architecture for relation classification (RC) that combines rule-based methods with contemporary deep learning techniques. This approach capitalizes on the strengths of both paradigms: the adaptability of rule-based systems and the generalization power of neural networks. Our architecture consists of two components: a declarative rule-based model for transparent classification and a neural component to enhance rule generalizability through semantic text matching. Notably, our semantic matcher is trained in an unsupervised domain-agnostic way, solely with synthetic data. Further, these components are loosely coupled, allowing for rule modifications without retraining the semantic matcher. In our evaluation, we focused on two few-shot relation classification datasets: Few-Shot TACRED and a Few-Shot version of NYT29. We show that our proposed method outperforms previous state-of-the-art models in three out of four settings, despite not seeing any human-annotated training data. Further, we show that our approach remains modular and pliable, i.e., the corresponding rules can be locally modified to improve the overall model. Human interventions to the rules for the TACRED relation \\texttt{org:parents} boost the performance on that relation by as much as 26\\% relative improvement, without negatively impacting the other relations, and without retraining the semantic matching component.",\n}\n\n
\n
\n\n\n
\n This paper introduces a novel neuro-symbolic architecture for relation classification (RC) that combines rule-based methods with contemporary deep learning techniques. This approach capitalizes on the strengths of both paradigms: the adaptability of rule-based systems and the generalization power of neural networks. Our architecture consists of two components: a declarative rule-based model for transparent classification and a neural component to enhance rule generalizability through semantic text matching. Notably, our semantic matcher is trained in an unsupervised domain-agnostic way, solely with synthetic data. Further, these components are loosely coupled, allowing for rule modifications without retraining the semantic matcher. In our evaluation, we focused on two few-shot relation classification datasets: Few-Shot TACRED and a Few-Shot version of NYT29. We show that our proposed method outperforms previous state-of-the-art models in three out of four settings, despite not seeing any human-annotated training data. Further, we show that our approach remains modular and pliable, i.e., the corresponding rules can be locally modified to improve the overall model. Human interventions to the rules for the TACRED relation \\textttorg:parents boost the performance on that relation by as much as 26% relative improvement, without negatively impacting the other relations, and without retraining the semantic matching component.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Active Learning Design Choices for NER with Transformers.\n \n \n \n\n\n \n Robert Vacareanu; Enrique Noriega-Atala; Gus Hahn-Powell; Marco A. Valenzuela-Escarcega; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation, Torino, Italy, May 2024. European Language Resources Association\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{vacareanu2024ActiveLearningNER,\n    title = "Active Learning Design Choices for NER with Transformers",\n    author = "Robert Vacareanu and Enrique Noriega-Atala and Gus Hahn-Powell and Marco A. Valenzuela-Escarcega and Mihai Surdeanu ",\n    booktitle = "Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation",\n    month = may,\n    year = "2024",\n    address = "Torino, Italy",\n    publisher = "European Language Resources Association",\n    abstract = "We explore multiple important choices that have not been analyzed in conjunction regarding active learning for token classification using transformer networks. These choices are: (i) how to select what to annotate, (ii) decide whether to annotate entire sentences or smaller sentence fragments, (iii) how to train with incomplete annotations at token-level, and (iv) how to select the initial seed dataset. We explore whether annotating at sub-sentence level can translate to an improved downstream performance by considering two different sub-sentence annotation strategies: (i) entity-level, and (ii) token-level. These approaches result in some sentences being only partially annotated. To address this issue, we introduce and evaluate multiple strategies to deal with partially-annotated sentences during the training process. We show that annotating at the sub-sentence level achieves comparable or better performance than sentence-level annotations with a smaller number of annotated tokens. We then explore the extent to which the performance gap remains once accounting for the annotation time and found that both annotation schemes perform similarly.",\n}\n\n
\n
\n\n\n
\n We explore multiple important choices that have not been analyzed in conjunction regarding active learning for token classification using transformer networks. These choices are: (i) how to select what to annotate, (ii) decide whether to annotate entire sentences or smaller sentence fragments, (iii) how to train with incomplete annotations at token-level, and (iv) how to select the initial seed dataset. We explore whether annotating at sub-sentence level can translate to an improved downstream performance by considering two different sub-sentence annotation strategies: (i) entity-level, and (ii) token-level. These approaches result in some sentences being only partially annotated. To address this issue, we introduce and evaluate multiple strategies to deal with partially-annotated sentences during the training process. We show that annotating at the sub-sentence level achieves comparable or better performance than sentence-level annotations with a smaller number of annotated tokens. We then explore the extent to which the performance gap remains once accounting for the annotation time and found that both annotation schemes perform similarly.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Weak Supervision Approach for Few-Shot Aspect Based Sentiment Analysis.\n \n \n \n \n\n\n \n Robert Vacareanu; Siddharth Varia; Kishaloy Halder; Shuai Wang; Giovanni Paolini; Neha Anna John; Miguel Ballesteros; and Smaranda Muresan.\n\n\n \n\n\n\n In Yvette Graham; and Matthew Purver., editor(s), Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2734–2752, St. Julian's, Malta, March 2024. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{vacareanu-etal-2024-weak,\n    title = "A Weak Supervision Approach for Few-Shot Aspect Based Sentiment Analysis",\n    author = "Vacareanu, Robert  and\n      Varia, Siddharth  and\n      Halder, Kishaloy  and\n      Wang, Shuai  and\n      Paolini, Giovanni  and\n      Anna John, Neha  and\n      Ballesteros, Miguel  and\n      Muresan, Smaranda",\n    editor = "Graham, Yvette  and\n      Purver, Matthew",\n    booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",\n    month = mar,\n    year = "2024",\n    address = "St. Julian{'}s, Malta",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.eacl-long.167",\n    pages = "2734--2752",\n    abstract = "We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks. We propose a pipeline approach to construct a noisy ABSA dataset, and we use it to adapt a pre-trained sequence-to-sequence model to the ABSA tasks. We test the resulting model on three widely used ABSA datasets, before and after fine-tuning. Our proposed method preserves the full fine-tuning performance while showing significant improvements (15.84 absolute F1) in the few-shot learning scenario for the harder tasks. In zero-shot (i.e., without fine-tuning), our method outperforms the previous state of the art on the aspect extraction sentiment classification (AESC) task and is, additionally, capable of performing the harder aspect sentiment triplet extraction (ASTE) task.",\n}\n\n
\n
\n\n\n
\n We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks. We propose a pipeline approach to construct a noisy ABSA dataset, and we use it to adapt a pre-trained sequence-to-sequence model to the ABSA tasks. We test the resulting model on three widely used ABSA datasets, before and after fine-tuning. Our proposed method preserves the full fine-tuning performance while showing significant improvements (15.84 absolute F1) in the few-shot learning scenario for the harder tasks. In zero-shot (i.e., without fine-tuning), our method outperforms the previous state of the art on the aspect extraction sentiment classification (AESC) task and is, additionally, capable of performing the harder aspect sentiment triplet extraction (ASTE) task.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains.\n \n \n \n\n\n \n Zijie Wang; Farzana Rashid; and Eduardo Blanco.\n\n\n \n\n\n\n In Findings of the Association for Computational Linguistics: NAACL 2024, Mexico City, Mexico, June 2024. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{wang2024naaclfindings,\n    title = "Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains",\n    author = "Wang, Zijie and Rashid, Farzana and Blanco, Eduardo",\n    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics"\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Time Travel in LLMs: Tracing Data Contamination in Large Language Models.\n \n \n \n \n\n\n \n Shahriar Golchin; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Twelfth International Conference on Learning Representations (ICLR), 2024. \n \n\n\n\n
\n\n\n\n \n \n \"TimePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 6 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{golchin2024time,\n\ttitle={Time Travel in {LLM}s: Tracing Data Contamination in Large Language Models},\n\tauthor={Shahriar Golchin and Mihai Surdeanu},\n\tbooktitle={Proceedings of the Twelfth International Conference on Learning Representations (ICLR)},\n\tyear={2024},\n\turl={https://openreview.net/forum?id=2Rwq6c3tvr}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation.\n \n \n \n \n\n\n \n Fahmida Alam; Md Asiful Islam; Robert Vacareanu; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Fourteenth Language Resources and Evaluation Conference, Torino, Italy, May 2024. European Language Resources Association\n \n\n\n\n
\n\n\n\n \n \n \"TowardsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{fahmida2024fs-meta-dataset,\n    title = "Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation",\n    author = "Fahmida Alam and Md Asiful Islam and Robert Vacareanu and Mihai Surdeanu ",\n    booktitle = "Proceedings of the Fourteenth Language Resources and Evaluation Conference",\n    month = may,\n    year = "2024",\n    address = "Torino, Italy",\n    publisher = "European Language Resources Association",\n    url = "http://arxiv.org/abs/2404.04445",\n    abstract = "We introduce a meta dataset for few-shot relation extraction, which includes two datasets derived from existing supervised relation extraction datasets – NYT29 (Takanobu et al. , 2019 ; Nayak and Ng , 2020) and WIKIDATA (Sorokin and Gurevych, 2017) – as well as a few-shot form of the TACRED dataset (Sabo et al., 2021). Importantly, all these few-shot datasets were generated under realistic assumptions such as: the test relations are different from any relations a model might have seen before, limited training data, and a preponderance of candidate relation mentions that do not correspond to any of the relations of interest. Using this large resource, we conduct a comprehensive evaluation of six recent few-shot relation extraction methods, and observe that no method comes out as a clear winner. Further, the overall performance on this task is low, indicating substantial need for future research. We release all versions of the data, i.e., both supervised and few-shot, for future research."\n}\n\n
\n
\n\n\n
\n We introduce a meta dataset for few-shot relation extraction, which includes two datasets derived from existing supervised relation extraction datasets – NYT29 (Takanobu et al. , 2019 ; Nayak and Ng , 2020) and WIKIDATA (Sorokin and Gurevych, 2017) – as well as a few-shot form of the TACRED dataset (Sabo et al., 2021). Importantly, all these few-shot datasets were generated under realistic assumptions such as: the test relations are different from any relations a model might have seen before, limited training data, and a preponderance of candidate relation mentions that do not correspond to any of the relations of interest. Using this large resource, we conduct a comprehensive evaluation of six recent few-shot relation extraction methods, and observe that no method comes out as a clear winner. Further, the overall performance on this task is low, indicating substantial need for future research. We release all versions of the data, i.e., both supervised and few-shot, for future research.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition.\n \n \n \n \n\n\n \n Haris Riaz; Razvan-Gabriel Dumitru; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation, Torino, Italy, May 2024. European Language Resources Association\n \n\n\n\n
\n\n\n\n \n \n \"ELLEN:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{riaz2024ellen,\n    title = "ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition",\n    author = "Haris Riaz and Razvan-Gabriel Dumitru and Mihai Surdeanu",\n    booktitle = "Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation",\n    month = may,\n    year = "2024",\n    address = "Torino, Italy",\n    publisher = "European Language Resources Association",\n    url = "https://arxiv.org/pdf/2403.17385.pdf",\n    abstract = "In this work, we revisit the problem of semi-supervised named entity recognition (NER) focusing on extremely light supervision, consisting of a lexicon containing only 10 examples per class. We introduce ELLEN, a simple, fully modular, neuro-symbolic method that blends fine-tuned language models with linguistic rules. These rules include insights such as ''One Sense Per Discourse'', using a Masked Language Model as an unsupervised NER, leveraging part-of-speech tags to identify and eliminate unlabeled entities as false negatives, and other intuitions about classifier confidence scores in local and global context. ELLEN achieves very strong performance on the CoNLL-2003 dataset when using the minimal supervision from the lexicon above. It also outperforms most existing (and considerably more complex) semi-supervised NER methods under the same supervision settings commonly used in the literature (i.e., 5% of the training data). Further, we evaluate our CoNLL-2003 model in a zero-shot scenario on WNUT-17 where we find that it outperforms GPT-3.5 and achieves comparable performance to GPT-4. In a zero-shot setting, ELLEN also achieves over 75% of the performance of a strong, fully supervised model trained on gold data. Our code is available at: https://github.com/hriaz17/ELLEN",\n}\n\n
\n
\n\n\n
\n In this work, we revisit the problem of semi-supervised named entity recognition (NER) focusing on extremely light supervision, consisting of a lexicon containing only 10 examples per class. We introduce ELLEN, a simple, fully modular, neuro-symbolic method that blends fine-tuned language models with linguistic rules. These rules include insights such as ''One Sense Per Discourse'', using a Masked Language Model as an unsupervised NER, leveraging part-of-speech tags to identify and eliminate unlabeled entities as false negatives, and other intuitions about classifier confidence scores in local and global context. ELLEN achieves very strong performance on the CoNLL-2003 dataset when using the minimal supervision from the lexicon above. It also outperforms most existing (and considerably more complex) semi-supervised NER methods under the same supervision settings commonly used in the literature (i.e., 5% of the training data). Further, we evaluate our CoNLL-2003 model in a zero-shot scenario on WNUT-17 where we find that it outperforms GPT-3.5 and achieves comparable performance to GPT-4. In a zero-shot setting, ELLEN also achieves over 75% of the performance of a strong, fully supervised model trained on gold data. Our code is available at: https://github.com/hriaz17/ELLEN\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n On Learning Bipolar Gradual Argumentation Semantics with Neural Networks.\n \n \n \n \n\n\n \n Caren Al Anaissy; Sandeep Suntwal; Mihai Surdeanu; and Srdjan Vesic.\n\n\n \n\n\n\n In Proceedings of the 16th International Conference on Agents and Artificial Intelligence (ICAART), 2024. \n \n\n\n\n
\n\n\n\n \n \n \"OnPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 11 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{anaissy-icaart2024,\n    title = "On Learning Bipolar Gradual Argumentation Semantics with Neural Networks",\n    author = "Caren Al Anaissy and Sandeep Suntwal and Mihai Surdeanu and Srdjan Vesic",\n    booktitle = "Proceedings of the 16th International Conference on Agents and Artificial Intelligence (ICAART)",\n    year = "2024",\n    url = "https://clulab.org/papers/icaart2024.pdf",\n    abstract = "Computational argumentation has evolved as a key area in artificial intelligence, used to analyze aspects of thinking, making decisions, and conversing. As a result, it is currently employed in a variety of real-world contexts, from legal reasoning to intelligence analysis. An argumentation framework is modelled as a graph where the nodes represent arguments and the edges of the graph represent relations (i.e., supports, attacks) between nodes. In this work, we investigate the ability of neural network methods to learn a gradual bipolar argumentation semantics, which allows for both supports and attacks. We begin by calculating the acceptability degrees for graph nodes. These scores are generated using Quantitative Argumentation Debate (QuAD) argumentation semantics. We apply this approach to two benchmark datasets: Twelve Angry Men and Debate- pedia. Using this data, we train and evaluate the performance of three benchmark architectures: Multilayer Perceptron (MLP), Graph Convolution Network (GCN), and Graph Attention Network (GAT) to learn the acceptability degree scores produced by the QuAD semantics. Our results show that these neural network methods can learn bipolar gradual argumentation semantics. The models trained on GCN architecture perform better than the other two architectures underscoring the importance of modelling argumentation graphs explicitly."\n}\n\n
\n
\n\n\n
\n Computational argumentation has evolved as a key area in artificial intelligence, used to analyze aspects of thinking, making decisions, and conversing. As a result, it is currently employed in a variety of real-world contexts, from legal reasoning to intelligence analysis. An argumentation framework is modelled as a graph where the nodes represent arguments and the edges of the graph represent relations (i.e., supports, attacks) between nodes. In this work, we investigate the ability of neural network methods to learn a gradual bipolar argumentation semantics, which allows for both supports and attacks. We begin by calculating the acceptability degrees for graph nodes. These scores are generated using Quantitative Argumentation Debate (QuAD) argumentation semantics. We apply this approach to two benchmark datasets: Twelve Angry Men and Debate- pedia. Using this data, we train and evaluate the performance of three benchmark architectures: Multilayer Perceptron (MLP), Graph Convolution Network (GCN), and Graph Attention Network (GAT) to learn the acceptability degree scores produced by the QuAD semantics. Our results show that these neural network methods can learn bipolar gradual argumentation semantics. The models trained on GCN architecture perform better than the other two architectures underscoring the importance of modelling argumentation graphs explicitly.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Metadata Enhancement Using Large Language Models.\n \n \n \n \n\n\n \n Hyunju Song; Steven Bethard; and Andrea Thomer.\n\n\n \n\n\n\n In Tirthankar Ghosal; Amanpreet Singh; Anita Waard; Philipp Mayr; Aakanksha Naik; Orion Weller; Yoonjoo Lee; Shannon Shen; and Yanxia Qin., editor(s), Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024), pages 145–154, Bangkok, Thailand, August 2024. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"MetadataPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{song-etal-2024-metadata,\n    title = "Metadata Enhancement Using Large Language Models",\n    author = "Song, Hyunju  and\n      Bethard, Steven  and\n      Thomer, Andrea",\n    editor = "Ghosal, Tirthankar  and\n      Singh, Amanpreet  and\n      Waard, Anita  and\n      Mayr, Philipp  and\n      Naik, Aakanksha  and\n      Weller, Orion  and\n      Lee, Yoonjoo  and\n      Shen, Shannon  and\n      Qin, Yanxia",\n    booktitle = "Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)",\n    month = aug,\n    year = "2024",\n    address = "Bangkok, Thailand",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.sdp-1.14",\n    pages = "145--154",\n    keywords = {workshop paper, term normalization},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n hinoki at SemEval-2024 Task 7: Numeral-Aware Headline Generation (English).\n \n \n \n \n\n\n \n Hinoki Crum; and Steven Bethard.\n\n\n \n\n\n\n In Atul Kr. Ojha; A. Seza Doğruöz; Harish Tayyar Madabushi; Giovanni Da San Martino; Sara Rosenthal; and Aiala Rosá., editor(s), Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 34–39, Mexico City, Mexico, June 2024. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"hinokiPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{crum-bethard-2024-hinoki,\n    title = "hinoki at {S}em{E}val-2024 Task 7: Numeral-Aware Headline Generation ({E}nglish)",\n    author = "Crum, Hinoki  and\n      Bethard, Steven",\n    editor = {Ojha, Atul Kr.  and\n      Do{\\u{g}}ru{\\"o}z, A. Seza  and\n      Tayyar Madabushi, Harish  and\n      Da San Martino, Giovanni  and\n      Rosenthal, Sara  and\n      Ros{\\'a}, Aiala},\n    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.semeval-1.6",\n    doi = "10.18653/v1/2024.semeval-1.6",\n    pages = "34--39",\n    keywords = {shared task paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning.\n \n \n \n \n\n\n \n Xin Su; Tiep Le; Steven Bethard; and Phillip Howard.\n\n\n \n\n\n\n In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 8597–8613, Mexico City, Mexico, June 2024. Association for Computational Linguistics\n [Acceptance rate 23%]\n\n\n\n
\n\n\n\n \n \n \"Semi-StructuredPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{su-etal-2024-semi,\n    title = "Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning",\n    author = "Su, Xin  and\n      Le, Tiep  and\n      Bethard, Steven  and\n      Howard, Phillip",\n    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.naacl-long.475",\n    doi = "10.18653/v1/2024.naacl-long.475",\n    pages = "8597--8613",\n    keywords = {question answering},\n    note = {[Acceptance rate 23\\%]},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Improving Toponym Resolution by Predicting Attributes to Constrain Geographical Ontology Entries.\n \n \n \n \n\n\n \n Zeyu Zhang; Egoitz Laparra; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 35–44, Mexico City, Mexico, June 2024. Association for Computational Linguistics\n [Acceptance rate 23%]\n\n\n\n
\n\n\n\n \n \n \"ImprovingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{zhang-etal-2024-improving-toponym,\n    title = "Improving Toponym Resolution by Predicting Attributes to Constrain Geographical Ontology Entries",\n    author = "Zhang, Zeyu  and\n      Laparra, Egoitz  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.naacl-short.3",\n    doi = "10.18653/v1/2024.naacl-short.3",\n    pages = "35--44",\n    keywords = {geospatial normalization, information extraction},\n    note = {[Acceptance rate 23\\%]},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of the 6th Clinical Natural Language Processing Workshop.\n \n \n \n \n\n\n \n Tristan Naumann; Asma Ben Abacha; Steven Bethard; Kirk Roberts; and Danielle Bitterman.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. Mexico City, Mexico, June 2024.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@proceedings{clinicalnlp-2024-clinical,\n    title = "Proceedings of the 6th Clinical Natural Language Processing Workshop",\n    editor = "Naumann, Tristan  and\n      Ben Abacha, Asma  and\n      Bethard, Steven  and\n      Roberts, Kirk  and\n      Bitterman, Danielle",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.clinicalnlp-1.0",\n    keywords = "health",\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Findings of the Association for Computational Linguistics: NAACL 2024.\n \n \n \n \n\n\n \n Kevin Duh; Helena Gomez; and Steven Bethard.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. Mexico City, Mexico, June 2024.\n \n\n\n\n
\n\n\n\n \n \n \"FindingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@proceedings{findings-2024-findings-association,\n    title = "Findings of the Association for Computational Linguistics: NAACL 2024",\n    editor = "Duh, Kevin  and\n      Gomez, Helena  and\n      Bethard, Steven",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.findings-naacl.0",\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).\n \n \n \n \n\n\n \n Kevin Duh; Helena Gomez; and Steven Bethard.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. Mexico City, Mexico, June 2024.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@proceedings{naacl-2024-long,\n    title = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",\n    editor = "Duh, Kevin  and\n      Gomez, Helena  and\n      Bethard, Steven",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.naacl-long.0",\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers).\n \n \n \n \n\n\n \n Kevin Duh; Helena Gomez; and Steven Bethard.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. Mexico City, Mexico, June 2024.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@proceedings{naacl-2024-short,\n    title = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",\n    editor = "Duh, Kevin  and\n      Gomez, Helena  and\n      Bethard, Steven",\n    month = jun,\n    year = "2024",\n    address = "Mexico City, Mexico",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2024.naacl-short.0",\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Machine Learning and Deep Learning Algorithms.\n \n \n \n \n\n\n \n Steven Bethard.\n\n\n \n\n\n\n In Hua Xu; and Dina Demner Fushman., editor(s), Natural Language Processing in Biomedicine: A Practical Guide, pages 43–76. Springer International Publishing, Cham, 2024.\n \n\n\n\n
\n\n\n\n \n \n \"MachinePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@incollection{Bethard2024,\nauthor="Bethard, Steven",\neditor="Xu, Hua\nand Demner Fushman, Dina",\ntitle="Machine Learning and Deep Learning Algorithms",\nbookTitle="Natural Language Processing in Biomedicine: A Practical Guide",\nyear="2024",\npublisher="Springer International Publishing",\naddress="Cham",\npages="43--76",\nisbn="978-3-031-55865-8",\ndoi="10.1007/978-3-031-55865-8_3",\nurl="https://doi.org/10.1007/978-3-031-55865-8_3",\nkeywords={machine learning},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A survey on geocoding: algorithms and datasets for toponym resolution.\n \n \n \n \n\n\n \n Zeyu Zhang; and Steven Bethard.\n\n\n \n\n\n\n Language Resources and Evaluation. June 2024.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{zhang_survey_2024,\n\ttitle = {A survey on geocoding: algorithms and datasets for toponym resolution},\n\tissn = {1574-0218},\n\tshorttitle = {A survey on geocoding},\n\turl = {https://doi.org/10.1007/s10579-024-09730-2},\n\tdoi = {10.1007/s10579-024-09730-2},\n\tlanguage = {en},\n\turldate = {2024-06-12},\n\tjournal = {Language Resources and Evaluation},\n\tauthor = {Zhang, Zeyu and Bethard, Steven},\n\tmonth = jun,\n\tyear = {2024},\n\tkeywords = {Geocoding, Geographical entity normalization, Toponym resolution},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Examining the Dynamics of Uncivil Discourse Between Sub-National Political Officials and the Public on Twitter.\n \n \n \n \n\n\n \n Juliana L. Barbati; Stephen A. Rains; Kate Kenski; Yotam Shmargad; Steven Bethard; and Kevin Coe.\n\n\n \n\n\n\n Mass Communication and Society, 0(0): 1-20. February 2024.\n \n\n\n\n
\n\n\n\n \n \n \"ExaminingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@article{barbati-etal-2024-examining,\nauthor = {Juliana L. Barbati and Stephen A. Rains and Kate Kenski and Yotam Shmargad and Steven Bethard and Kevin Coe},\ntitle = {Examining the Dynamics of Uncivil Discourse Between Sub-National Political Officials and the Public on Twitter},\njournal = {Mass Communication and Society},\nvolume = {0},\nnumber = {0},\npages = {1-20},\nmonth = feb,\nyear = {2024},\npublisher = {Routledge},\nurl = {https://doi.org/10.1080/15205436.2024.2313095},\nkeywords = {social media, civility},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2023\n \n \n (24)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n The ToMCAT Dataset.\n \n \n \n \n\n\n \n Adarsh Pyarelal; Eric Duong; Caleb Jones Shibu; Paulo Soares; Savannah Boyd; Payal Khosla; Valeria Pfeifer; Diheng Zhang; Eric S Andrews; Rick Champlin; Vincent Paul Raymond; Meghavarshini Krishnaswamy; Clayton Morrison; Emily Butler; and Kobus Barnard.\n\n\n \n\n\n\n In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2023. \n \n\n\n\n
\n\n\n\n \n \n \"ThePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{\n    pyarelal2023the,\n    title={The To{MCAT} Dataset},\n    author={Adarsh Pyarelal and Eric Duong and Caleb Jones Shibu and Paulo Soares and Savannah Boyd and Payal Khosla and Valeria Pfeifer and Diheng Zhang and Eric S Andrews and Rick Champlin and Vincent Paul Raymond and Meghavarshini Krishnaswamy and Clayton Morrison and Emily Butler and Kobus Barnard},\n    booktitle={Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track},\n    year={2023},\n    url={https://openreview.net/forum?id=ZJWQfgXQb6}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Who is Speaking? Speaker-Aware Multiparty Dialogue Act Classification.\n \n \n \n \n\n\n \n Ayesha Qamar; Adarsh Pyarelal; and Ruihong Huang.\n\n\n \n\n\n\n In Houda Bouamor; Juan Pino; and Kalika Bali., editor(s), Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10122–10135, Singapore, December 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"WhoPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{qamar-etal-2023-speaking,\n    title = "Who is Speaking? Speaker-Aware Multiparty Dialogue Act Classification",\n    author = "Qamar, Ayesha  and\n      Pyarelal, Adarsh  and\n      Huang, Ruihong",\n    editor = "Bouamor, Houda  and\n      Pino, Juan  and\n      Bali, Kalika",\n    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",\n    month = dec,\n    year = "2023",\n    address = "Singapore",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.findings-emnlp.678",\n    pages = "10122--10135",\n    abstract = "Utterances do not occur in isolation in dialogues; it is essential to have the information of who the speaker of an utterance is to be able to recover the speaker{'}s intention with respect to the surrounding context. Beyond simply capturing speaker switches, identifying how speakers interact with each other in a dialogue is crucial to understanding conversational flow. This becomes increasingly important and simultaneously difficult to model when more than two interlocutors take part in a conversation. To overcome this challenge, we propose to explicitly add speaker awareness to each utterance representation. To that end, we use a graph neural network to model how each speaker is behaving within the local context of a conversation. The speaker representations learned this way are then used to update their respective utterance representations. We experiment with both multiparticipant and dyadic conversations on the MRDA and SwDA datasets and show the effectiveness of our approach.",\n}\n\n
\n
\n\n\n
\n Utterances do not occur in isolation in dialogues; it is essential to have the information of who the speaker of an utterance is to be able to recover the speaker's intention with respect to the surrounding context. Beyond simply capturing speaker switches, identifying how speakers interact with each other in a dialogue is crucial to understanding conversational flow. This becomes increasingly important and simultaneously difficult to model when more than two interlocutors take part in a conversation. To overcome this challenge, we propose to explicitly add speaker awareness to each utterance representation. To that end, we use a graph neural network to model how each speaker is behaving within the local context of a conversation. The speaker representations learned this way are then used to update their respective utterance representations. We experiment with both multiparticipant and dyadic conversations on the MRDA and SwDA datasets and show the effectiveness of our approach.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Hierarchical Fusion for Online Multimodal Dialog Act Classification.\n \n \n \n \n\n\n \n Md Messal Monem Miah; Adarsh Pyarelal; and Ruihong Huang.\n\n\n \n\n\n\n In Houda Bouamor; Juan Pino; and Kalika Bali., editor(s), Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7532–7545, Singapore, December 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"HierarchicalPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{miah-etal-2023-hierarchical,\n    title = "Hierarchical Fusion for Online Multimodal Dialog Act Classification",\n    author = "Miah, Md Messal Monem  and\n      Pyarelal, Adarsh  and\n      Huang, Ruihong",\n    editor = "Bouamor, Houda  and\n      Pino, Juan  and\n      Bali, Kalika",\n    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",\n    month = dec,\n    year = "2023",\n    address = "Singapore",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.findings-emnlp.505",\n    pages = "7532--7545",\n    abstract = "We propose a framework for online multimodal dialog act (DA) classification based on raw audio and ASR-generated transcriptions of current and past utterances. Existing multimodal DA classification approaches are limited by ineffective audio modeling and late-stage fusion. We showcase significant improvements in multimodal DA classification by integrating modalities at a more granular level and incorporating recent advancements in large language and audio models for audio feature extraction. We further investigate the effectiveness of self-attention and cross-attention mechanisms in modeling utterances and dialogs for DA classification. We achieve a substantial increase of 3 percentage points in the F1 score relative to current state-of-the-art models on two prominent DA classification datasets, MRDA and EMOTyDA.",\n}\n\n
\n
\n\n\n
\n We propose a framework for online multimodal dialog act (DA) classification based on raw audio and ASR-generated transcriptions of current and past utterances. Existing multimodal DA classification approaches are limited by ineffective audio modeling and late-stage fusion. We showcase significant improvements in multimodal DA classification by integrating modalities at a more granular level and incorporating recent advancements in large language and audio models for audio feature extraction. We further investigate the effectiveness of self-attention and cross-attention mechanisms in modeling utterances and dialogs for DA classification. We achieve a substantial increase of 3 percentage points in the F1 score relative to current state-of-the-art models on two prominent DA classification datasets, MRDA and EMOTyDA.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Hiding in Plain Sight: Tweets with Hate Speech Masked by Homoglyphs.\n \n \n \n \n\n\n \n Portia Cooper; Mihai Surdeanu; and Eduardo Blanco.\n\n\n \n\n\n\n In Houda Bouamor; Juan Pino; and Kalika Bali., editor(s), Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2922–2929, Singapore, December 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"HidingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{cooper-etal-2023-hiding,\n    title = "Hiding in Plain Sight: Tweets with Hate Speech Masked by Homoglyphs",\n    author = "Cooper, Portia  and\n      Surdeanu, Mihai  and\n      Blanco, Eduardo",\n    editor = "Bouamor, Houda  and\n      Pino, Juan  and\n      Bali, Kalika",\n    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",\n    month = dec,\n    year = "2023",\n    address = "Singapore",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.findings-emnlp.192",\n    doi = "10.18653/v1/2023.findings-emnlp.192",\n    pages = "2922--2929",\n    abstract = "To avoid detection by current NLP monitoring applications, progenitors of hate speech often replace one or more letters in offensive words with homoglyphs, visually similar Unicode characters. Harvesting real-world hate speech containing homoglyphs is challenging due to the vast replacement possibilities. We developed a character substitution scraping method and assembled the Offensive Tweets with Homoglyphs (OTH) Dataset (N=90,788) with more than 1.5 million occurrences of 1,281 non-Latin characters (emojis excluded). In an annotated sample (n=700), 40.14{\\%} of the tweets were found to contain hate speech. We assessed the performance of seven transformer-based hate speech detection models and found that they performed poorly in a zero-shot setting (F1 scores between 0.04 and 0.52) but normalizing the data dramatically improved detection (F1 scores between 0.59 and 0.71). Training the models using the annotated data further boosted performance (highest micro-averaged F1 score=0.88, using five-fold cross validation). This study indicates that a dataset containing homoglyphs known and unknown to the scraping script can be collected, and that neural models can be trained to recognize camouflaged real-world hate speech.",\n}\n\n
\n
\n\n\n
\n To avoid detection by current NLP monitoring applications, progenitors of hate speech often replace one or more letters in offensive words with homoglyphs, visually similar Unicode characters. Harvesting real-world hate speech containing homoglyphs is challenging due to the vast replacement possibilities. We developed a character substitution scraping method and assembled the Offensive Tweets with Homoglyphs (OTH) Dataset (N=90,788) with more than 1.5 million occurrences of 1,281 non-Latin characters (emojis excluded). In an annotated sample (n=700), 40.14% of the tweets were found to contain hate speech. We assessed the performance of seven transformer-based hate speech detection models and found that they performed poorly in a zero-shot setting (F1 scores between 0.04 and 0.52) but normalizing the data dramatically improved detection (F1 scores between 0.59 and 0.71). Training the models using the annotated data further boosted performance (highest micro-averaged F1 score=0.88, using five-fold cross validation). This study indicates that a dataset containing homoglyphs known and unknown to the scraping script can be collected, and that neural models can be trained to recognize camouflaged real-world hate speech.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Transferring Legal Natural Language Inference Model from a US State to Another: What Makes It So Hard?.\n \n \n \n \n\n\n \n Alice Kwak; Gaetano Forte; Derek Bambauer; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Natural Legal Language Processing Workshop 2023, December 2023. \n \n\n\n\n
\n\n\n\n \n \n \"TransferringPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{kwak-et-al-nllp2023-error-analysis,\n    title = "Transferring Legal Natural Language Inference Model from a US State to Another: What Makes It So Hard?",\n    author = "Alice Kwak and Gaetano Forte and Derek Bambauer and Mihai Surdeanu",\n    booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2023",\n    month = dec,\n    year = "2023",\n    url = "https://clulab.org/papers/nllp2023_kwak-et-al.pdf",\n    abstract = "This study investigates whether a legal natural language inference (NLI) model trained on the data from one US state can be transferred to another state. We fine-tuned a pre-trained model on the task of evaluating the validity of legal will statements, once with the dataset containing the Tennessee wills and once with the dataset containing the Idaho wills. Each model’s performance on the in-domain setting and the out-of-domain setting are compared to see if the models can across the states. We found that the model trained on one US state can be mostly transferred to another state. However, it is clear that the model’s performance drops in the out-of-domain setting. The F1 scores of the Tennessee model and the Idaho model are 96.41 and 92.03 when predicting the data from the same state, but they drop to 66.32 and 81.60 when predicting the data from another state. Subsequent error analysis revealed that there are two major sources of errors. First, the model fails to recognize equivalent laws across states when there are stylistic differences between laws. Second, difference in statutory section numbering system between the states makes it difficult for the model to locate laws relevant to the cases being predicted on. This analysis provides insights on how the future NLI system can be improved. Also, our findings offer empirical support to legal experts advocating the standardization of legal documents.",\n}\n\n
\n
\n\n\n
\n This study investigates whether a legal natural language inference (NLI) model trained on the data from one US state can be transferred to another state. We fine-tuned a pre-trained model on the task of evaluating the validity of legal will statements, once with the dataset containing the Tennessee wills and once with the dataset containing the Idaho wills. Each model’s performance on the in-domain setting and the out-of-domain setting are compared to see if the models can across the states. We found that the model trained on one US state can be mostly transferred to another state. However, it is clear that the model’s performance drops in the out-of-domain setting. The F1 scores of the Tennessee model and the Idaho model are 96.41 and 92.03 when predicting the data from the same state, but they drop to 66.32 and 81.60 when predicting the data from another state. Subsequent error analysis revealed that there are two major sources of errors. First, the model fails to recognize equivalent laws across states when there are stylistic differences between laws. Second, difference in statutory section numbering system between the states makes it difficult for the model to locate laws relevant to the cases being predicted on. This analysis provides insights on how the future NLI system can be improved. Also, our findings offer empirical support to legal experts advocating the standardization of legal documents.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Information Extraction from Legal Wills: How Well Does GPT-4 Do?.\n \n \n \n \n\n\n \n Alice Kwak; Cheonkam Jeong; Gaetano Forte; Derek Bambauer; Clayton Morrison; and Mihai Surdeanu.\n\n\n \n\n\n\n In Findings of the Association for Computational Linguistics: EMNLP 2023, December 2023. \n \n\n\n\n
\n\n\n\n \n \n \"InformationPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{kwak-et-al-emnlp2023-ie4wills,\n    title = "Information Extraction from Legal Wills: How Well Does GPT-4 Do?",\n    author = "Alice Kwak and Cheonkam Jeong and Gaetano Forte and Derek Bambauer and Clayton Morrison and Mihai Surdeanu",\n    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",\n    month = dec,\n    year = "2023",\n    url = "https://clulab.org/papers/emnlp2023_kwak-et-al.pdf",\n    abstract = "This work presents a manually annotated dataset for Information Extraction (IE) from legal wills, and relevant in-context learning experiments on the dataset. The dataset consists of entities, binary relations between the entities (e.g., relations between testator and beneficiary), and n-ary events (e.g., bequest) extracted from 45 legal wills from two US states. This dataset can serve as a foundation for downstream tasks in the legal domain. Another use case of this dataset is evaluating the performance of large language models (LLMs) on this IE task. We evaluated GPT-4 with our dataset to investigate its ability to extract information from legal wills. Our evaluation result demonstrates that the model is capable of handling the task reasonably well. When given instructions and examples as a prompt, GPT-4 shows decent performance for both entity extraction and relation extraction tasks. Nevertheless, the evaluation result also reveals that the model is not perfect. We observed inconsistent outputs (given a prompt) as well as prompt over-generalization.",\n}\n\n
\n
\n\n\n
\n This work presents a manually annotated dataset for Information Extraction (IE) from legal wills, and relevant in-context learning experiments on the dataset. The dataset consists of entities, binary relations between the entities (e.g., relations between testator and beneficiary), and n-ary events (e.g., bequest) extracted from 45 legal wills from two US states. This dataset can serve as a foundation for downstream tasks in the legal domain. Another use case of this dataset is evaluating the performance of large language models (LLMs) on this IE task. We evaluated GPT-4 with our dataset to investigate its ability to extract information from legal wills. Our evaluation result demonstrates that the model is capable of handling the task reasonably well. When given instructions and examples as a prompt, GPT-4 shows decent performance for both entity extraction and relation extraction tasks. Nevertheless, the evaluation result also reveals that the model is not perfect. We observed inconsistent outputs (given a prompt) as well as prompt over-generalization.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Improving Zero-shot Relation Classification via Automatically-acquired Entailment Templates.\n \n \n \n \n\n\n \n Mahdi Rahimi; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023), pages 187–195, Toronto, Canada, July 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ImprovingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{rahimi-surdeanu-2023-improving,\n    title = "Improving Zero-shot Relation Classification via Automatically-acquired Entailment Templates",\n    author = "Rahimi, Mahdi  and\n      Surdeanu, Mihai",\n    booktitle = "Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.repl4nlp-1.16",\n    pages = "187--195",\n    abstract = "While fully supervised relation classification (RC) models perform well on large-scale datasets, their performance drops drastically in low-resource settings. As generating annotated examples are expensive, recent zero-shot methods have been proposed that reformulate RC into other NLP tasks for which supervision exists such as textual entailment. However, these methods rely on templates that are manually created which is costly and requires domain expertise. In this paper, we present a novel strategy for template generation for relation classification, which is based on adapting Harris{'} distributional similarity principle to templates encoded using contextualized representations. Further, we perform empirical evaluation of different strategies for combining the automatically acquired templates with manual templates. The experimental results on TACRED show that our approach not only performs better than the zero-shot RC methods that only use manual templates, but also that it achieves state-of-the-art performance for zero-shot TACRED at 64.3 F1 score.",\n}\n\n
\n
\n\n\n
\n While fully supervised relation classification (RC) models perform well on large-scale datasets, their performance drops drastically in low-resource settings. As generating annotated examples are expensive, recent zero-shot methods have been proposed that reformulate RC into other NLP tasks for which supervision exists such as textual entailment. However, these methods rely on templates that are manually created which is costly and requires domain expertise. In this paper, we present a novel strategy for template generation for relation classification, which is based on adapting Harris' distributional similarity principle to templates encoded using contextualized representations. Further, we perform empirical evaluation of different strategies for combining the automatically acquired templates with manual templates. The experimental results on TACRED show that our approach not only performs better than the zero-shot RC methods that only use manual templates, but also that it achieves state-of-the-art performance for zero-shot TACRED at 64.3 F1 score.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n It's not Sexually Suggestive; It's Educative | Separating Sex Education from Suggestive Content on TikTok Videos.\n \n \n \n \n\n\n \n Enfa George; and Mihai Surdeanu.\n\n\n \n\n\n\n In Findings of the Association for Computational Linguistics: ACL 2023, pages 5904–5915, Toronto, Canada, July 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"It'sPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{george-surdeanu-2023-sexually,\n    title = "It{'}s not Sexually Suggestive; It{'}s Educative | Separating Sex Education from Suggestive Content on {T}ik{T}ok Videos",\n    author = "George, Enfa  and\n      Surdeanu, Mihai",\n    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.findings-acl.365",\n    pages = "5904--5915",\n    abstract = "We introduce SexTok, a multi-modal dataset composed of TikTok videos labeled as sexually suggestive (from the annotator{'}s point of view), sex-educational content, or neither. Such a dataset is necessary to address the challenge of distinguishing between sexually suggestive content and virtual sex education videos on TikTok. Children{'}s exposure to sexually suggestive videos has been shown to have adversarial effects on their development (Collins et al. 2017). Meanwhile, virtual sex education, especially on subjects that are more relevant to the LGBTQIA+ community, is very valuable (Mitchell et al. 2014). The platform{'}s current system removes/punishes some of both types of videos, even though they serve different purposes. Our dataset contains video URLs, and it is also audio transcribed. To validate its importance, we explore two transformer-based models for classifying the videos. Our preliminary results suggest that the task of distinguishing between these types of videos is learnable but challenging. These experiments suggest that this dataset is meaningful and invites further study on the subject.",\n}\n\n
\n
\n\n\n
\n We introduce SexTok, a multi-modal dataset composed of TikTok videos labeled as sexually suggestive (from the annotator's point of view), sex-educational content, or neither. Such a dataset is necessary to address the challenge of distinguishing between sexually suggestive content and virtual sex education videos on TikTok. Children's exposure to sexually suggestive videos has been shown to have adversarial effects on their development (Collins et al. 2017). Meanwhile, virtual sex education, especially on subjects that are more relevant to the LGBTQIA+ community, is very valuable (Mitchell et al. 2014). The platform's current system removes/punishes some of both types of videos, even though they serve different purposes. Our dataset contains video URLs, and it is also audio transcribed. To validate its importance, we explore two transformer-based models for classifying the videos. Our preliminary results suggest that the task of distinguishing between these types of videos is learnable but challenging. These experiments suggest that this dataset is meaningful and invites further study on the subject.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers.\n \n \n \n \n\n\n \n Zheng Tang; and Mihai Surdeanu.\n\n\n \n\n\n\n Computational Linguistics, 49(1): 117-156. 03 2023.\n \n\n\n\n
\n\n\n\n \n \n \"ItPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 44 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{10.1162/coli_a_00463,\n    author = {Tang, Zheng and Surdeanu, Mihai},\n    title = "{It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers}",\n    journal = {Computational Linguistics},\n    volume = {49},\n    number = {1},\n    pages = {117-156},\n    year = {2023},\n    month = {03},\n    abstract = "{We propose an explainable approach for relation extraction that mitigates the tension between generalization and explainability by jointly training for the two goals. Our approach uses a multi-task learning architecture, which jointly trains a classifier for relation extraction, and a sequence model that labels words in the context of the relations that explain the decisions of the relation classifier. We also convert the model outputs to rules to bring global explanations to this approach. This sequence model is trained using a hybrid strategy: supervised, when supervision from pre-existing patterns is available, and semi-supervised otherwise. In the latter situation, we treat the sequence model’s labels as latent variables, and learn the best assignment that maximizes the performance of the relation classifier. We evaluate the proposed approach on the two datasets and show that the sequence model provides labels that serve as accurate explanations for the relation classifier’s decisions, and, importantly, that the joint training generally improves the performance of the relation classifier. We also evaluate the performance of the generated rules and show that the new rules are a great add-on to the manual rules and bring the rule-based system much closer to the neural models.}",\n    issn = {0891-2017},\n    doi = {10.1162/coli_a_00463},\n    url = {https://doi.org/10.1162/coli\\_a\\_00463},\n    eprint = {https://direct.mit.edu/coli/article-pdf/49/1/117/2068962/coli\\_a\\_00463.pdf},\n}\n
\n
\n\n\n
\n We propose an explainable approach for relation extraction that mitigates the tension between generalization and explainability by jointly training for the two goals. Our approach uses a multi-task learning architecture, which jointly trains a classifier for relation extraction, and a sequence model that labels words in the context of the relations that explain the decisions of the relation classifier. We also convert the model outputs to rules to bring global explanations to this approach. This sequence model is trained using a hybrid strategy: supervised, when supervision from pre-existing patterns is available, and semi-supervised otherwise. In the latter situation, we treat the sequence model’s labels as latent variables, and learn the best assignment that maximizes the performance of the relation classifier. We evaluate the proposed approach on the two datasets and show that the sequence model provides labels that serve as accurate explanations for the relation classifier’s decisions, and, importantly, that the joint training generally improves the performance of the relation classifier. We also evaluate the performance of the generated rules and show that the new rules are a great add-on to the manual rules and bring the rule-based system much closer to the neural models.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n NEUROSTRUCTURAL DECODING: Neural Text Generation with Structural Constraints.\n \n \n \n \n\n\n \n Mohaddeseh Bastan; Mihai Surdeanu; and Niranjan Balasubramanian.\n\n\n \n\n\n\n In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), 2023. \n \n\n\n\n
\n\n\n\n \n \n \"NEUROSTRUCTURALPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 7 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{bastan2023-structural,\n  title={NEUROSTRUCTURAL DECODING: Neural Text Generation with Structural Constraints},\n  author={Bastan, Mohaddeseh and Surdeanu, Mihai and Balasubramanian, Niranjan},\n  booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL)},\n  year={2023},\n  url={https://aclanthology.org/2023.acl-long.528.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Bootstrapping Neural Relation and Explanation Classifiers.\n \n \n \n \n\n\n \n Zheng Tang; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), July 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"BootstrappingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 10 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{acl2023-bootstrapping-zheng,\n    title = "Bootstrapping Neural Relation and Explanation Classifiers",\n    author = "Zheng Tang  and\n      Surdeanu, Mihai",\n    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL)",\n    month = jul,\n    year = "2023",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.acl-short.5.pdf",\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Annotating and Training for Population Subjective Views.\n \n \n \n \n\n\n \n Maria Alexeeva; Caroline Hyland; Keith Alcock; Allegra A. Beal Cohen; Hubert Kanyamahanga; Isaac Kobby Anni; and Mihai Surdeanu.\n\n\n \n\n\n\n In 13th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, 2023. \n \n\n\n\n
\n\n\n\n \n \n \"AnnotatingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{\n    alexeeva-et-al-2023-annotating,\n    title={Annotating and Training for Population Subjective Views},\n    author={Alexeeva, Maria and Hyland, Caroline and Alcock, Keith and Beal Cohen,  Allegra A. and Kanyamahanga, Hubert and Anni, Isaac Kobby and Surdeanu, Mihai},\n    booktitle={13th Workshop on Computational Approaches to Subjectivity, Sentiment {\\&} Social Media Analysis},\n    year={2023},\n    url={http://clulab.org/papers/wassa2023-beliefs.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering.\n \n \n \n \n\n\n \n Xin Su; Phillip Howard; Nagib Hakim; and Steven Bethard.\n\n\n \n\n\n\n In Houda Bouamor; Juan Pino; and Kalika Bali., editor(s), Findings of the Association for Computational Linguistics: EMNLP 2023, pages 948–966, Singapore, December 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"FusingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{su-etal-2023-fusing,\n    title = "Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering",\n    author = "Su, Xin  and\n      Howard, Phillip  and\n      Hakim, Nagib  and\n      Bethard, Steven",\n    editor = "Bouamor, Houda  and\n      Pino, Juan  and\n      Bali, Kalika",\n    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",\n    month = dec,\n    year = "2023",\n    address = "Singapore",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.findings-emnlp.67",\n    doi = "10.18653/v1/2023.findings-emnlp.67",\n    pages = "948--966",\n    keywords = {timelines, question answering},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of the 5th Clinical Natural Language Processing Workshop.\n \n \n \n \n\n\n \n Tristan Naumann; Asma Ben Abacha; Steven Bethard; Kirk Roberts; and Anna Rumshisky.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. Toronto, Canada, July 2023.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@proceedings{clinicalnlp-2023-clinical,\n    title = "Proceedings of the 5th Clinical Natural Language Processing Workshop",\n    editor = "Naumann, Tristan  and\n      Ben Abacha, Asma  and\n      Bethard, Steven  and\n      Roberts, Kirk  and\n      Rumshisky, Anna",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.clinicalnlp-1.0",\n    keywords = {health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Transformer-based cynical expression detection in a corpus of Spanish YouTube reviews.\n \n \n \n \n\n\n \n Samuel Gonzalez-Lopez; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 194–201, Toronto, Canada, July 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Transformer-basedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{gonzalez-lopez-bethard-2023-transformer,\n    title = "Transformer-based cynical expression detection in a corpus of {S}panish {Y}ou{T}ube reviews",\n    author = "Gonzalez-Lopez, Samuel  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, {\\&} Social Media Analysis",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.wassa-1.18",\n    pages = "194--201",\n    keywords = {workshop paper, social media, sentiment},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage Resolution.\n \n \n \n \n\n\n \n Zeyu Zhang; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the The 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023), pages 48–60, Toronto, Canada, July 2023. Association for Computational Linguistics\n [Acceptance rate 47%]\n\n\n\n
\n\n\n\n \n \n \"ImprovingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{zhang-bethard-2023-improving,\n    title = "Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage Resolution",\n    author = "Zhang, Zeyu  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the The 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.starsem-1.6",\n    pages = "48--60",\n    keywords = {locations, information extraction},\n    note = {[Acceptance rate 47\\%]},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Arizonans at SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis with XLM-T.\n \n \n \n \n\n\n \n Nimet Beyza Bozdag; Tugay Bilgis; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1656–1659, Toronto, Canada, July 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ArizonansPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{bozdag-etal-2023-arizonans,\n    title = "Arizonans at {S}em{E}val-2023 Task 9: Multilingual Tweet Intimacy Analysis with {XLM}-{T}",\n    author = "Bozdag, Nimet Beyza  and\n      Bilgis, Tugay  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023)",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.semeval-1.230",\n    pages = "1656--1659",\n    keywords = {shared task paper, social media},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Gallagher at SemEval-2023 Task 5: Tackling Clickbait with Seq2Seq Models.\n \n \n \n \n\n\n \n Tugay Bilgis; Nimet Beyza Bozdag; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1650–1655, Toronto, Canada, July 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"GallagherPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{bilgis-etal-2023-gallagher,\n    title = "Gallagher at {S}em{E}val-2023 Task 5: Tackling Clickbait with {S}eq2{S}eq Models",\n    author = "Bilgis, Tugay  and\n      Bozdag, Nimet Beyza  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023)",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.semeval-1.229",\n    pages = "1650--1655",\n    keywords = {shared task paper, social media},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Textual Entailment for Temporal Dependency Graph Parsing.\n \n \n \n \n\n\n \n Jiarui Yao; Steven Bethard; Kristin Wright-Bettner; Eli Goldner; David Harris; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 191–199, Toronto, Canada, July 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"TextualPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{yao-etal-2023-textual,\n    title = "Textual Entailment for Temporal Dependency Graph Parsing",\n    author = "Yao, Jiarui  and\n      Bethard, Steven  and\n      Wright-Bettner, Kristin  and\n      Goldner, Eli  and\n      Harris, David  and\n      Savova, Guergana",\n    booktitle = "Proceedings of the 5th Clinical Natural Language Processing Workshop",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.clinicalnlp-1.25",\n    pages = "191--199",\n    keywords = {workshop paper, timelines, information extraction, health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n clulab at MEDIQA-Chat 2023: Summarization and classification of medical dialogues.\n \n \n \n \n\n\n \n Kadir Bulut Ozler; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 144–149, Toronto, Canada, July 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"clulabPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{ozler-bethard-2023-clulab,\n    title = "clulab at {MEDIQA}-Chat 2023: Summarization and classification of medical dialogues",\n    author = "Ozler, Kadir Bulut  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 5th Clinical Natural Language Processing Workshop",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.clinicalnlp-1.19",\n    pages = "144--149",\n    keywords = {shared task paper, health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n End-to-end clinical temporal information extraction with multi-head attention.\n \n \n \n \n\n\n \n Timothy Miller; Steven Bethard; Dmitriy Dligach; and Guergana Savova.\n\n\n \n\n\n\n In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, pages 313–319, Toronto, Canada, July 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"End-to-endPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{miller-etal-2023-end,\n    title = "End-to-end clinical temporal information extraction with multi-head attention",\n    author = "Miller, Timothy  and\n      Bethard, Steven  and\n      Dligach, Dmitriy  and\n      Savova, Guergana",\n    booktitle = "The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.bionlp-1.28",\n    pages = "313--319",\n    keywords = {workshop paper, timelines, information extraction, health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Two-Stage Fine-Tuning for Improved Bias and Variance for Large Pretrained Language Models.\n \n \n \n \n\n\n \n Lijing Wang; Yingya Li; Timothy Miller; Steven Bethard; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15746–15761, Toronto, Canada, July 2023. Association for Computational Linguistics\n [Acceptance rate 23%]\n\n\n\n
\n\n\n\n \n \n \"Two-StagePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{wang-etal-2023-two,\n    title = "Two-Stage Fine-Tuning for Improved Bias and Variance for Large Pretrained Language Models",\n    author = "Wang, Lijing  and\n      Li, Yingya  and\n      Miller, Timothy  and\n      Bethard, Steven  and\n      Savova, Guergana",\n    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",\n    month = jul,\n    year = "2023",\n    address = "Toronto, Canada",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2023.acl-long.877",\n    pages = "15746--15761",\n    keywords = {machine learning},\n    note = {[Acceptance rate 23\\%]},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Addressing structural hurdles for metadata extraction from environmental impact statements.\n \n \n \n \n\n\n \n Egoitz Laparra; Alex Binford-Walsh; Kirk Emerson; Marc L. Miller; Laura López-Hoffman; Faiz Currim; and Steven Bethard.\n\n\n \n\n\n\n Journal of the Association for Information Science and Technology, n/a(n/a). June 2023.\n \n\n\n\n
\n\n\n\n \n \n \"AddressingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@article{https://doi.org/10.1002/asi.24809,\nauthor = {Laparra, Egoitz and Binford-Walsh, Alex and Emerson, Kirk and Miller, Marc L. and López-Hoffman, Laura and Currim, Faiz and Bethard, Steven},\ntitle = {Addressing structural hurdles for metadata extraction from environmental impact statements},\njournal = {Journal of the Association for Information Science and Technology},\nvolume = {n/a},\nnumber = {n/a},\npages = {},\nmonth = jun,\nyear = {2023},\ndoi = {https://doi.org/10.1002/asi.24809},\nurl = {https://asistdl.onlinelibrary.wiley.com/doi/abs/10.1002/asi.24809},\nkeywords = {environmental policy},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Engagement with incivility in tweets from and directed at local elected officials.\n \n \n \n \n\n\n \n Stephen A. Rains; Kate Kenski; Leah Dajches; Kaylin Duncan; Kun Yan; Yejin Shin; Jules L. Barbati; Steven Bethard; Kevin Coe; and Yotam Shmargad.\n\n\n \n\n\n\n Communication and Democracy, 57(1): 143-152. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"EngagementPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@article{doi:10.1080/27671127.2023.2195467,\nauthor = {Stephen A. Rains and Kate Kenski and Leah Dajches and Kaylin Duncan and Kun Yan and Yejin Shin and Jules L. Barbati and Steven Bethard and Kevin Coe and Yotam Shmargad},\ntitle = {Engagement with incivility in tweets from and directed at local elected officials},\njournal = {Communication and Democracy},\nvolume = {57},\nnumber = {1},\npages = {143-152},\nyear  = {2023},\npublisher = {Routledge},\ndoi = {10.1080/27671127.2023.2195467},\nURL = {https://doi.org/10.1080/27671127.2023.2195467},\nkeywords = {social media},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2022\n \n \n (24)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n PatternRank: Jointly Ranking Patterns and Extractions for Relation Extraction Using Graph-Based Algorithms.\n \n \n \n \n\n\n \n Robert Vacareanu; Dane Bell; and Mihai Surdeanu.\n\n\n \n\n\n\n In PANDL, 2022. \n \n\n\n\n
\n\n\n\n \n \n \"PatternRank:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Vacareanu2022PatternRankJR,\n    title = {PatternRank: Jointly Ranking Patterns and Extractions for Relation Extraction Using Graph-Based Algorithms},\n    author = {Robert Vacareanu and Dane Bell and Mihai Surdeanu},\n    booktitle = {PANDL},\n    abstract="{In this paper we revisit the direction of using lexico-syntactic patterns for relation extraction instead of today's ubiquitous neural classifiers. We propose a semi-supervised graph-based algorithm for pattern acquisition that scores patterns and the relations they extract jointly, using a variant of PageRank. We insert light supervision in the form of seed patterns or relations, and model it with several custom teleportation probabilities that bias random-walk scores of patterns/relations based on their proximity to correct information. We evaluate our approach on Few-Shot TACRED, and show that our method outperforms (or performs competitively with) more expensive and opaque deep neural networks. Lastly, we thoroughly compare our proposed approach with the seminal RlogF pattern acquisition algorithm of, showing that it outperforms it for all the hyper parameters tested, in all settings. }",\n    url = {https://aclanthology.org/2022.pandl-1.1.pdf},\n    year = {2022}\n}\n\n
\n
\n\n\n
\n In this paper we revisit the direction of using lexico-syntactic patterns for relation extraction instead of today's ubiquitous neural classifiers. We propose a semi-supervised graph-based algorithm for pattern acquisition that scores patterns and the relations they extract jointly, using a variant of PageRank. We insert light supervision in the form of seed patterns or relations, and model it with several custom teleportation probabilities that bias random-walk scores of patterns/relations based on their proximity to correct information. We evaluate our approach on Few-Shot TACRED, and show that our method outperforms (or performs competitively with) more expensive and opaque deep neural networks. Lastly, we thoroughly compare our proposed approach with the seminal RlogF pattern acquisition algorithm of, showing that it outperforms it for all the hyper parameters tested, in all settings. \n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction.\n \n \n \n \n\n\n \n Robert Vacareanu; George Caique Gouveia Barbosa; Enrique Noriega-Atala; Gus Hahn-Powell; Rebecca Sharp; Marco Antonio Valenzuela-Escarcega; and Mihai Surdeanu.\n\n\n \n\n\n\n Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Vacareanu2022AHI,\n    title = {A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction},\n    author = {Robert Vacareanu and George Caique Gouveia Barbosa and Enrique Noriega-Atala and Gus Hahn-Powell and Rebecca Sharp and Marco Antonio Valenzuela-Escarcega and Mihai Surdeanu},\n    journal = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations},\n    abstract = "{We propose a system that assists a user in constructing transparent information extraction models, consisting of patterns (or rules) written in a declarative language, through program synthesis.Users of our system can specify their requirements through the use of examples,which are collected with a search interface.The rule-synthesis system proposes rule candidates and the results of applying them on a textual corpus; the user has the option to accept the candidate, request another option, or adjust the examples provided to the system.Through an interactive evaluation, we show that our approach generates high-precision rules even in a 1-shot setting. On a second evaluation on a widely-used relation extraction dataset (TACRED), our method generates rules that outperform considerably manually written patterns.Our code, demo, and documentation is available at https://clulab.github.io/odinsynth.}",\n    url = {https://aclanthology.org/2022.naacl-demo.8.pdf},\n    year = {2022}\n}\n\n
\n
\n\n\n
\n We propose a system that assists a user in constructing transparent information extraction models, consisting of patterns (or rules) written in a declarative language, through program synthesis.Users of our system can specify their requirements through the use of examples,which are collected with a search interface.The rule-synthesis system proposes rule candidates and the results of applying them on a textual corpus; the user has the option to accept the candidate, request another option, or adjust the examples provided to the system.Through an interactive evaluation, we show that our approach generates high-precision rules even in a 1-shot setting. On a second evaluation on a widely-used relation extraction dataset (TACRED), our method generates rules that outperform considerably manually written patterns.Our code, demo, and documentation is available at https://clulab.github.io/odinsynth.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Rule Based Event Extraction for Artificial Social Intelligence.\n \n \n \n \n\n\n \n Remo Nitschke; Yuwei Wang; Chen; Adarsh Pyarelal; and Rebecca Sharp.\n\n\n \n\n\n\n In Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning, pages 71–84, Gyeongju, Republic of Korea, October 2022. International Conference on Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"RulePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{nitschke-etal-2022-rule,\n    title = "Rule Based Event Extraction for Artificial Social Intelligence",\n    author = "Nitschke, Remo  and\n      Wang, Yuwei  and\n      Chen, Chen  and\n      Pyarelal, Adarsh  and\n      Sharp, Rebecca",\n    booktitle = "Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",\n    month = oct,\n    year = "2022",\n    address = "Gyeongju, Republic of Korea",\n    publisher = "International Conference on Computational Linguistics",\n    url = "https://aclanthology.org/2022.pandl-1.9",\n    pages = "71--84",\n    abstract = "Natural language (as opposed to structured communication modes\n        such as Morse code) is by far the most common mode of communication\n        between humans, and can thus provide significant insight into both\n        individual mental states and interpersonal dynamics. As part of\n        DARPA{'}s Artificial Social Intelligence for Successful Teams (ASIST)\n        program, we are developing an AI agent team member that constructs and\n        maintains models of their human teammates and provides appropriate\n        task-relevant advice to improve team processes and mission performance.\n        One of the key components of this agent is a module that uses a\n        rule-based approach to extract task-relevant events from natural\n        language utterances in real time, and publish them for consumption by\n        downstream components. In this case study, we evaluate the performance\n        of our rule-based event extraction system on a recently conducted ASIST\n        experiment consisting of a simulated urban search and rescue mission in\n        Minecraft. We compare the performance of our approach with that of a\n        zero-shot neural classifier, and find that our approach outperforms the\n        classifier for all event types, even when the classifier is used in an\n        oracle setting where it knows how many events should be extracted from\n        each utterance.",\n}\n\n
\n
\n\n\n
\n Natural language (as opposed to structured communication modes such as Morse code) is by far the most common mode of communication between humans, and can thus provide significant insight into both individual mental states and interpersonal dynamics. As part of DARPA's Artificial Social Intelligence for Successful Teams (ASIST) program, we are developing an AI agent team member that constructs and maintains models of their human teammates and provides appropriate task-relevant advice to improve team processes and mission performance. One of the key components of this agent is a module that uses a rule-based approach to extract task-relevant events from natural language utterances in real time, and publish them for consumption by downstream components. In this case study, we evaluate the performance of our rule-based event extraction system on a recently conducted ASIST experiment consisting of a simulated urban search and rescue mission in Minecraft. We compare the performance of our approach with that of a zero-shot neural classifier, and find that our approach outperforms the classifier for all event types, even when the classifier is used in an oracle setting where it knows how many events should be extracted from each utterance.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n SuMe: A Dataset Towards Summarizing Biomedical Mechanisms.\n \n \n \n \n\n\n \n Mohaddeseh Bastan; Nishant Shankar; Mihai Surdeanu; and Niranjan Balasubramanian.\n\n\n \n\n\n\n In Proceedings of the 2022 LREC Conference, 2022. \n \n\n\n\n
\n\n\n\n \n \n \"SuMe:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 10 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{bastan2022-sume,\n  title={SuMe: A Dataset Towards Summarizing Biomedical Mechanisms},\n  author={Bastan, Mohaddeseh and Shankar, Nishant and Surdeanu, Mihai and Balasubramanian, Niranjan},\n  booktitle={Proceedings of the 2022 LREC Conference},\n  year={2022},\n  url={http://clulab.org/papers/SuMe_LREC2022.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Do Transformer Networks Improve the Discovery of Rules from Text?.\n \n \n \n \n\n\n \n Mahdi Rahimi; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 13th Language Resources and Evaluation Conference (LREC), 2022. \n \n\n\n\n
\n\n\n\n \n \n \"DoPaper\n  \n \n \n \"Do poster\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 26 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{rahimi2022bird,\n  title={Do Transformer Networks Improve the Discovery of Rules from Text?},\n  author={Rahimi, Mahdi and Surdeanu, Mihai},\n  booktitle={Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},\n  year={2022},\n  url={http://clulab.org/papers/bird.pdf},\n  url_Poster={http://clulab.org/papers/can_poster.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A STEP towards Interpretable Multi-Hop Reasoning: Bridge Phrase Identification and Query Expansion.\n \n \n \n \n\n\n \n Fan Luo; and Mihai Surdeanu.\n\n\n \n\n\n\n In The 13th edition of Language Resources and Evaluation Conference Processing, 2022. European Language Resource Association (ELRA)\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{bridgephrases-identification2022,\n  title={A STEP towards Interpretable Multi-Hop Reasoning: Bridge Phrase Identification and Query Expansion},\n  author={Fan Luo and\n        Mihai Surdeanu},\n  booktitle = {The 13th edition of Language Resources and Evaluation Conference Processing},\n  year={2022},\n  abstract = {We propose an unsupervised method for the identification of bridge phrases in multi-hop question answering (QA). Our method\nconstructs a graph of noun phrases from the question and the available context, and applies the Steiner tree algorithm to identify\nthe minimal sub-graph that connects all question phrases. Nodes in the sub-graph that bridge loosely-connected or disjoint\nsubsets of question phrases due to low-strength semantic relations are extracted as bridge phrases. The identified bridge phrases\nare then used to expand the query based on the initial question, helping in increasing the relevance of evidence that has little\nlexical overlap or semantic relation with the question. Through an evaluation on HotpotQA(Yang et al., 2018), a popular dataset\nfor multi-hop QA, we show that our method yields: (a) improved evidence retrieval, (b) improved QA performance when using\nthe retrieved sentences; and (c) effective and faithful explanations when answers are provided.},\n  organization={European Language Resource Association (ELRA)},\n  url={http://clulab.org/papers/bridgephrases.pdf}\n}\n\n
\n
\n\n\n
\n We propose an unsupervised method for the identification of bridge phrases in multi-hop question answering (QA). Our method constructs a graph of noun phrases from the question and the available context, and applies the Steiner tree algorithm to identify the minimal sub-graph that connects all question phrases. Nodes in the sub-graph that bridge loosely-connected or disjoint subsets of question phrases due to low-strength semantic relations are extracted as bridge phrases. The identified bridge phrases are then used to expand the query based on the initial question, helping in increasing the relevance of evidence that has little lexical overlap or semantic relation with the question. Through an evaluation on HotpotQA(Yang et al., 2018), a popular dataset for multi-hop QA, we show that our method yields: (a) improved evidence retrieval, (b) improved QA performance when using the retrieved sentences; and (c) effective and faithful explanations when answers are provided.\n
\n\n\n
\n\n\n \n\n\n
\n \n\n \n \n \n \n \n \n Automatic Correction of Syntactic Dependency Annotation Differences.\n \n \n \n \n\n\n \n Andrew Zupon; Andrew Carnie; Michael Hammond; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 13th Language Resources and Evaluation Conference (LREC), 2022. \n \n\n\n\n
\n\n\n\n \n \n \"AutomaticPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{zupon2022lparsinglrec,\n\ttitle={Automatic Correction of Syntactic Dependency Annotation Differences},\n\tauthor={Zupon, Andrew and Carnie, Andrew and Hammond, Michael and Surdeanu, Mihai},\n\tbooktitle={Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},\n\tyear={2022},\n\turl={http://clulab.org/papers/lrec-parsing.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Learning Open Domain Multi-hop Search Using Reinforcement Learning.\n \n \n \n \n\n\n \n Enrique Noriega-Atala; Mihai Surdeanu; and Clayton T. Morrison.\n\n\n \n\n\n\n In Proceedings of the Workshop on Structured and Unstructured Knowledge Integration, Seattle, Washington, July 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"LearningPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{https://doi.org/10.48550/arxiv.2205.15281,\n  doi = {10.48550/ARXIV.2205.15281},\n  url = {https://arxiv.org/abs/2205.15281},\n  author = {Noriega-Atala, Enrique and Surdeanu, Mihai and Morrison, Clayton T.},\n  title = {Learning Open Domain Multi-hop Search Using Reinforcement Learning},\n  booktitle = "Proceedings of the Workshop on Structured and Unstructured Knowledge Integration",\n  month = jul,\n  year = "2022",\n  address = "Seattle, Washington",\n  publisher = "Association for Computational Linguistics",\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction.\n \n \n \n \n\n\n \n Robert Vacareanu; Marco A. Valenzuela-Escárcega; George Barbosa; Rebecca Sharp; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 13th Language Resources and Evaluation Conference (LREC), 2022. \n \n\n\n\n
\n\n\n\n \n \n \"FromPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 16 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{vacareanu2022synthlrec,\n        title={From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction},\n        author={Vacareanu, Robert and Valenzuela-Esc\\'{a}rcega, Marco A. and Barbosa, George and Sharp, Rebecca and Surdeanu, Mihai},\n        booktitle={Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},\n        year={2022},\n        url={https://arxiv.org/abs/2202.00475},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Answering Geosciences Research Questions at a Global Scale via a Hybrid Machine-Human Learning Approach: A Case Study of the Link between Climate and Volcanism.\n \n \n \n \n\n\n \n Seongjin Park; Barbara Carrapa; Mihai N. Ducea; Mihai Surdeanu; Robert Hayes; and Dan Collins.\n\n\n \n\n\n\n GSA Today. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"AnsweringPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 6 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@Article{park2022geo,\n  title     = {Answering Geosciences Research Questions at a Global Scale via a Hybrid Machine-Human Learning Approach: A Case Study of the Link between Climate and Volcanism},\n  author  = {Park, Seongjin and Carrapa, Barbara and Ducea, Mihai N. and Surdeanu, Mihai and Hayes, Robert and Collins, Dan},\n  journal = {GSA Today},\n  url = {https://www.geosociety.org/GSA/Publications/GSA_Today/GSA/GSAToday/science/G528A/article.aspx},\n  doi = {https://doi.org/10.1130/GSATG528A.1},\n  year = {2022}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples.\n \n \n \n \n\n\n \n Mohaddeseh Bastan; Mihai Surdeanu; and Niranjan Balasubramanian.\n\n\n \n\n\n\n In Findings of the Association for Computational Linguistics: EMNLP 2022, 2022. \n \n\n\n\n
\n\n\n\n \n \n \"BioNLI:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 6 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{bastan-etal-2022-bionli,\n    title = "BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples",\n    author = "Bastan, Mohaddeseh and Surdeanu, Mihai and Balasubramanian, Niranjan ",\n    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",\n    year = "2022",\n    url = "https://paperswithcode.com/paper/bionli-generating-a-biomedical-nli-dataset",\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Validity Assessment of Legal Will Statements as Natural Language Inference.\n \n \n \n \n\n\n \n Alice S. Kwak; Jacob O. Israelsen; Clayton T. Morrison; Derek E. Bambauer; and Mihai Surdeanu.\n\n\n \n\n\n\n In Findings of the Association for Computational Linguistics: EMNLP 2022, 2022. \n \n\n\n\n
\n\n\n\n \n \n \"ValidityPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{kwak-etal-2022-legalnli,\n    title = "Validity Assessment of Legal Will Statements as Natural Language Inference",\n    author = "Kwak, Alice S. and Israelsen, Jacob O. and Morrison, Clayton T. and Bambauer, Derek E. and Surdeanu, Mihai",\n    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",\n    year = "2022",\n    url = "http://clulab.org/papers/kwak2022.pdf",\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n We need to talk about random seeds.\n \n \n \n \n\n\n \n Steven Bethard.\n\n\n \n\n\n\n October 2022.\n \n\n\n\n
\n\n\n\n \n \n \"WePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 6 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@misc{https://doi.org/10.48550/arxiv.2210.13393,\n  doi = {10.48550/ARXIV.2210.13393},\n  url = {https://arxiv.org/abs/2210.13393},\n  author = {Bethard, Steven},\n  keywords = {machine learning},\n  title = {We need to talk about random seeds},\n  organization = {arXiv},\n  year = {2022},\n  month = oct,\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Engagement with partisan Russian troll tweets during the 2016 U.S. presidential election: a social identity perspective.\n \n \n \n \n\n\n \n Stephen A Rains; Jake Harwood; Yotam Shmargad; Kate Kenski; Kevin Coe; and Steven Bethard.\n\n\n \n\n\n\n Journal of Communication, 73(1): 38-48. 12 2022.\n \n\n\n\n
\n\n\n\n \n \n \"EngagementPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@article{10.1093/joc/jqac037,\n    author = {Rains, Stephen A and Harwood, Jake and Shmargad, Yotam and Kenski, Kate and Coe, Kevin and Bethard, Steven},\n    title = {Engagement with partisan Russian troll tweets during the 2016 U.S. presidential election: a social identity perspective},\n    journal = {Journal of Communication},\n    volume = {73},\n    number = {1},\n    pages = {38-48},\n    year = {2022},\n    month = {12},\n    issn = {0021-9916},\n    doi = {10.1093/joc/jqac037},\n    url = {https://doi.org/10.1093/joc/jqac037},\n    keywords = {social media},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Toward NEPA performance: A framework for assessing EIAs.\n \n \n \n \n\n\n \n Kirk Emerson; Elizabeth Baldwin; Tyler A. Scott; Justin R. Pidot; Aaron M. Lien; Faiz Currim; Steven Bethard; Sudha Ram; Marc L. Miller; and Laura López-Hoffman.\n\n\n \n\n\n\n Environmental Impact Assessment Review, 97: 106879. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"TowardPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@article{EMERSON2022106879,\ntitle = {Toward NEPA performance: A framework for assessing EIAs},\njournal = {Environmental Impact Assessment Review},\nvolume = {97},\npages = {106879},\nyear = {2022},\nissn = {0195-9255},\ndoi = {https://doi.org/10.1016/j.eiar.2022.106879},\nurl = {https://www.sciencedirect.com/science/article/pii/S0195925522001457},\nauthor = {Kirk Emerson and Elizabeth Baldwin and Tyler A. Scott and Justin R. Pidot and Aaron M. Lien and Faiz Currim and Steven Bethard and Sudha Ram and Marc L. Miller and Laura López-Hoffman},\nkeywords = {environmental policy},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of the 4th Clinical Natural Language Processing Workshop.\n \n \n \n \n\n\n \n Tristan Naumann; Steven Bethard; Kirk Roberts; and Anna Rumshisky.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. Seattle, WA, July 2022.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@proceedings{clinicalnlp-2022-clinical,\n    title = "Proceedings of the 4th Clinical Natural Language Processing Workshop",\n    editor = "Naumann, Tristan  and\n      Bethard, Steven  and\n      Roberts, Kirk  and\n      Rumshisky, Anna",\n    month = jul,\n    year = "2022",\n    address = "Seattle, WA",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2022.clinicalnlp-1.0",\n    keywords = {health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Ensemble-based Fine-Tuning Strategy for Temporal Relation Extraction from the Clinical Narrative.\n \n \n \n \n\n\n \n Lijing Wang; Timothy Miller; Steven Bethard; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the 4th Clinical Natural Language Processing Workshop, pages 103–108, Seattle, WA, July 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Ensemble-basedPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{wang-etal-2022-ensemble,\n    title = "Ensemble-based Fine-Tuning Strategy for Temporal Relation Extraction from the Clinical Narrative",\n    author = "Wang, Lijing  and\n      Miller, Timothy  and\n      Bethard, Steven  and\n      Savova, Guergana",\n    booktitle = "Proceedings of the 4th Clinical Natural Language Processing Workshop",\n    month = jul,\n    year = "2022",\n    address = "Seattle, WA",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2022.clinicalnlp-1.11",\n    doi = "10.18653/v1/2022.clinicalnlp-1.11",\n    pages = "103--108",\n    keywords = {workshop paper, timelines, information extraction, health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Exploring Text Representations for Generative Temporal Relation Extraction.\n \n \n \n \n\n\n \n Dmitriy Dligach; Steven Bethard; Timothy Miller; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the 4th Clinical Natural Language Processing Workshop, pages 109–113, Seattle, WA, July 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ExploringPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{dligach-etal-2022-exploring,\n    title = "Exploring Text Representations for Generative Temporal Relation Extraction",\n    author = "Dligach, Dmitriy  and\n      Bethard, Steven  and\n      Miller, Timothy  and\n      Savova, Guergana",\n    booktitle = "Proceedings of the 4th Clinical Natural Language Processing Workshop",\n    month = jul,\n    year = "2022",\n    address = "Seattle, WA",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2022.clinicalnlp-1.12",\n    doi = "10.18653/v1/2022.clinicalnlp-1.12",\n    pages = "109--113",\n    keywords = {workshop paper, timelines, information extraction, health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Exploring transformers and time lag features for predicting changes in mood over time.\n \n \n \n \n\n\n \n John Culnan; Damian Romero Diaz; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology, pages 226–231, Seattle, USA, July 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ExploringPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{culnan-etal-2022-exploring,\n    title = "Exploring transformers and time lag features for predicting changes in mood over time",\n    author = "Culnan, John  and\n      Romero Diaz, Damian  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology",\n    month = jul,\n    year = "2022",\n    address = "Seattle, USA",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2022.clpsych-1.21",\n    doi = "10.18653/v1/2022.clpsych-1.21",\n    pages = "226--231",\n    keywords = {shared task paper, social media, health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla.\n \n \n \n \n\n\n \n Nazia Tasnim; Md. Istiak Shihab; Asif Shahriyar Sushmit; Steven Bethard; and Farig Sadeque.\n\n\n \n\n\n\n In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1524–1530, Seattle, United States, July 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"TEAM-AtreidesPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{tasnim-etal-2022-team,\n    title = "{TEAM}-Atreides at {S}em{E}val-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in {B}angla",\n    author = "Tasnim, Nazia  and\n      Shihab, Md. Istiak  and\n      Shahriyar Sushmit, Asif  and\n      Bethard, Steven  and\n      Sadeque, Farig",\n    booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",\n    month = jul,\n    year = "2022",\n    address = "Seattle, United States",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2022.semeval-1.209",\n    doi = "10.18653/v1/2022.semeval-1.209",\n    pages = "1524--1530",\n    keywords = {shared task paper, information extraction},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n UA-KO at SemEval-2022 Task 11: Data Augmentation and Ensembles for Korean Named Entity Recognition.\n \n \n \n \n\n\n \n Hyunju Song; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1608–1612, Seattle, United States, July 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"UA-KOPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{song-bethard-2022-ua,\n    title = "{UA}-{KO} at {S}em{E}val-2022 Task 11: Data Augmentation and Ensembles for {K}orean Named Entity Recognition",\n    author = "Song, Hyunju  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",\n    month = jul,\n    year = "2022",\n    address = "Seattle, United States",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2022.semeval-1.222",\n    doi = "10.18653/v1/2022.semeval-1.222",\n    pages = "1608--1612",\n    keywords = {shared task paper, information extraction},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction.\n \n \n \n \n\n\n \n Mihai Surdeanu; John Hungerford; Yee Seng Chan; Jessica MacBride; Benjamin Gyori; Andrew Zupon; Zheng Tang; Haoling Qiu; Bonan Min; Yan Zverev; Caitlin Hilverman; Max Thomas; Walter Andrews; Keith Alcock; Zeyu Zhang; Michael Reynolds; Steven Bethard; Rebecca Sharp; and Egoitz Laparra.\n\n\n \n\n\n\n In Proceedings of the Second Workshop on Bridging Human–Computer Interaction and Natural Language Processing, pages 1–10, Seattle, Washington, July 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"TaxonomyPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{surdeanu-etal-2022-taxonomy,\n    title = "Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction",\n    author = "Surdeanu, Mihai  and\n      Hungerford, John  and\n      Chan, Yee Seng  and\n      MacBride, Jessica  and\n      Gyori, Benjamin  and\n      Zupon, Andrew  and\n      Tang, Zheng  and\n      Qiu, Haoling  and\n      Min, Bonan  and\n      Zverev, Yan  and\n      Hilverman, Caitlin  and\n      Thomas, Max  and\n      Andrews, Walter  and\n      Alcock, Keith  and\n      Zhang, Zeyu  and\n      Reynolds, Michael  and\n      Bethard, Steven  and\n      Sharp, Rebecca  and\n      Laparra, Egoitz",\n    booktitle = "Proceedings of the Second Workshop on Bridging Human--Computer Interaction and Natural Language Processing",\n    month = jul,\n    year = "2022",\n    address = "Seattle, Washington",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2022.hcinlp-1.1",\n    doi = "10.18653/v1/2022.hcinlp-1.1",\n    pages = "1--10",\n    keywords = {demo paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Comparison of Strategies for Source-Free Domain Adaptation.\n \n \n \n \n\n\n \n Xin Su; Yiyun Zhao; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8352–8367, Dublin, Ireland, May 2022. Association for Computational Linguistics\n [Acceptance rate 21%]\n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{su-etal-2022-comparison,\n    title = "A Comparison of Strategies for Source-Free Domain Adaptation",\n    author = "Su, Xin  and\n      Zhao, Yiyun  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",\n    month = may,\n    year = "2022",\n    address = "Dublin, Ireland",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2022.acl-long.572",\n    pages = "8352--8367",\n    keywords = {domain adaptation},\n    note = {[Acceptance rate 21\\%]},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2021\n \n \n (21)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Data and Model Distillation as a Solution for Domain-transferable Fact Verification.\n \n \n \n \n\n\n \n Mitch Mithun; Sandeep Suntwal; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021. \n \n\n\n\n
\n\n\n\n \n \n \"DataPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 12 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{mithun2020modeldis,\n  title={Data and Model Distillation as a Solution for Domain-transferable Fact Verification},\n  author={Mithun, Mitch and Suntwal, Sandeep and Surdeanu, Mihai},\n  booktitle={Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},\n  url={http://clulab.org/papers/knowledge_disillation.pdf},\n  year={2021}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Using the Hammer Only on Nails: A Hybrid Method for Representation-based Evidence Retrieval for Question Answering.\n \n \n \n \n\n\n \n Zhengzhong Liang; Yiyun Zhao; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of 43rd European Conference on IR Research, ECIR 2021, 2021. \n \n\n\n\n
\n\n\n\n \n \n \"UsingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 13 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{liang2021using,\n  title={Using the Hammer Only on Nails: A Hybrid Method for Representation-based Evidence Retrieval for Question Answering},\n  author={Liang, Zhengzhong and Zhao, Yiyun and Surdeanu, Mihai},\n  booktitle={Proceedings of 43rd European Conference on IR Research, ECIR 2021},\n  url={http://clulab.org/papers/ecir2021-hybrid.pdf},\n  year={2021}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Interpretability Rules: Jointly Bootstrapping a Neural Relation Extractor with an Explanation Decoder.\n \n \n \n \n\n\n \n Zheng Tang; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: TrustNLP Workshop, 2021. \n \n\n\n\n
\n\n\n\n \n \n \"InterpretabilityPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 23 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{zheng-tang-2021-edin,\n    title = "Interpretability Rules: Jointly Bootstrapping a Neural Relation Extractor with an Explanation Decoder",\n    author = "Tang, Zheng and Surdeanu, Mihai",\n    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: TrustNLP Workshop",\n    year = "2021",\n    url = "http://clulab.org/papers/trustNLP2021_edin.pdf"\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Me, myself, and ire: Effects of automatic transcription quality on emotion, sarcasm, and personality detection.\n \n \n \n \n\n\n \n John Culnan; Seongjin Park; Meghavarshini Krishnaswamy; and Rebecca Sharp.\n\n\n \n\n\n\n In Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 250–256, April 2021. \n \n\n\n\n
\n\n\n\n \n \n \"Me,Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{culnan-etal-2021-ire,\n    title = "Me, myself, and ire: Effects of automatic transcription quality on emotion, sarcasm, and personality detection",\n    author = "Culnan, John  and\n      Park, Seongjin  and\n      Krishnaswamy, Meghavarshini  and\n      Sharp, Rebecca",\n    booktitle = "Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis",\n    month = apr,\n    year = "2021",\n    url = "https://www.aclweb.org/anthology/2021.wassa-1.26",\n    pages = "250--256"\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading.\n \n \n \n \n\n\n \n Hoang Van; Vikas Yadav; and M. Surdeanu.\n\n\n \n\n\n\n ArXiv, abs/2106.04134. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"CheapPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Van2021CheapAG,\n  title={Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading},\n  author={Hoang Van and Vikas Yadav and M. Surdeanu},\n  journal={ArXiv},\n  year={2021},\n  volume={abs/2106.04134},\n  url={https://arxiv.org/pdf/2106.04134.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Students Who Study Together Learn Better: On the Importance of Collective Knowledge Distillation for Domain Transfer in Fact Verification.\n \n \n \n \n\n\n \n Mitch Paul Mithun; Sandeep Suntwal; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6968–6973, 2021. \n \n\n\n\n
\n\n\n\n \n \n \"StudentsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{mithun2021students,\n  title={Students Who Study Together Learn Better: On the Importance of Collective Knowledge Distillation for Domain Transfer in Fact Verification},\n  author={Mithun, Mitch Paul and Suntwal, Sandeep and Surdeanu, Mihai},\n  booktitle={Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},\n  pages={6968--6973},\n  year={2021},\n  url={https://aclanthology.org/2021.emnlp-main.558.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks.\n \n \n \n \n\n\n \n Hoang Van; Zheng Tang; and Mihai Surdeanu.\n\n\n \n\n\n\n In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4074–4080, Punta Cana, Dominican Republic, November 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"HowPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 9 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{van-etal-2021-may-help,\n    title = "How May {I} Help You? Using Neural Text Simplification to Improve Downstream {NLP} Tasks",\n    author = "Van, Hoang  and\n      Tang, Zheng  and\n      Surdeanu, Mihai",\n    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",\n    month = nov,\n    year = "2021",\n    address = "Punta Cana, Dominican Republic",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2021.findings-emnlp.343",\n    pages = "4074--4080",\n    abstract = "The general goal of text simplification (TS) is to reduce text complexity for human consumption. In this paper, we investigate another potential use of neural TS: assisting machines performing natural language processing (NLP) tasks. We evaluate the use of neural TS in two ways: simplifying input texts at prediction time and augmenting data to provide machines with additional information during training. We demonstrate that the latter scenario provides positive effects on machine performance on two separate datasets. In particular, the latter use of TS improves the performances of LSTM (1.82{--}1.98{\\%}) and SpanBERT (0.7{--}1.3{\\%}) extractors on TACRED, a complex, large-scale, real-world relation extraction task. Further, the same setting yields improvements of up to 0.65{\\%} matched and 0.62{\\%} mismatched accuracies for a BERT text classifier on MNLI, a practical natural language inference dataset.",\n}\n
\n
\n\n\n
\n The general goal of text simplification (TS) is to reduce text complexity for human consumption. In this paper, we investigate another potential use of neural TS: assisting machines performing natural language processing (NLP) tasks. We evaluate the use of neural TS in two ways: simplifying input texts at prediction time and augmenting data to provide machines with additional information during training. We demonstrate that the latter scenario provides positive effects on machine performance on two separate datasets. In particular, the latter use of TS improves the performances of LSTM (1.82–1.98%) and SpanBERT (0.7–1.3%) extractors on TACRED, a complex, large-scale, real-world relation extraction task. Further, the same setting yields improvements of up to 0.65% matched and 0.62% mismatched accuracies for a BERT text classifier on MNLI, a practical natural language inference dataset.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Neural Architectures for Biological Inter-Sentence Relation Extraction.\n \n \n \n\n\n \n Enrique Noriega-Atala; Peter M. Lovett; Clayton T. Morrison; and Mihai Surdeanu.\n\n\n \n\n\n\n 2021.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@misc{noriegaatala2021neural,\n      title={Neural Architectures for Biological Inter-Sentence Relation Extraction},\n      author={Enrique Noriega-Atala and Peter M. Lovett and Clayton T. Morrison and Mihai Surdeanu},\n      year={2021},\n      eprint={2112.09288},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Detection of Puffery on the English Wikipedia.\n \n \n \n \n\n\n \n Amanda Bertsch; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 329–333, Online, November 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"DetectionPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{bertsch-bethard-2021-detection,\n    title = "Detection of Puffery on the {E}nglish {W}ikipedia",\n    author = "Bertsch, Amanda  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)",\n    month = nov,\n    year = "2021",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2021.wnut-1.36",\n    pages = "329--333",\n    keywords = {social media, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Simplifying annotation of intersections in time normalization annotation: exploring syntactic and semantic validation.\n \n \n \n \n\n\n \n Peiwen Su; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop, pages 106–111, Punta Cana, Dominican Republic, November 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"SimplifyingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{su-bethard-2021-simplifying,\n    title = "Simplifying annotation of intersections in time normalization annotation: exploring syntactic and semantic validation",\n    author = "Su, Peiwen  and\n      Bethard, Steven",\n    booktitle = "Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop",\n    month = nov,\n    year = "2021",\n    address = "Punta Cana, Dominican Republic",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2021.law-1.11",\n    pages = "106--111",\n    keywords = {timelines, annotation, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Do pretrained transformers infer telicity like humans?.\n \n \n \n \n\n\n \n Yiyun Zhao; Jian Gang Ngui; Lucy Hall Hartley; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 25th Conference on Computational Natural Language Learning, pages 72–81, Online, November 2021. Association for Computational Linguistics\n [Acceptance rate 23%]\n\n\n\n
\n\n\n\n \n \n \"DoPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{zhao-etal-2021-pretrained,\n    title = "Do pretrained transformers infer telicity like humans?",\n    author = "Zhao, Yiyun  and\n      Ngui, Jian Gang  and\n      Hall Hartley, Lucy  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 25th Conference on Computational Natural Language Learning",\n    month = nov,\n    year = "2021",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2021.conll-1.6",\n    pages = "72--81",\n    keywords = {timelines, machine learning},\n    note = {[Acceptance rate 23\\%]},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Assessing the Russian Troll Efforts to Sow Discord on Twitter during the 2016 U.S. Election.\n \n \n \n \n\n\n \n Stephen A Rains; Yotam Shmargad; Kevin Coe; Kate Kenski; and Steven Bethard.\n\n\n \n\n\n\n Human Communication Research, 47(4): 477-486. 08 2021.\n \n\n\n\n
\n\n\n\n \n \n \"AssessingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@article{rains-etal-2021-hcr,\n    author = {Rains, Stephen A and Shmargad, Yotam and Coe, Kevin and Kenski, Kate and Bethard, Steven},\n    title = {Assessing the Russian Troll Efforts to Sow Discord on Twitter during the 2016 U.S. Election},\n    journal = {Human Communication Research},\n    volume = {47},\n    number = {4},\n    pages = {477-486},\n    year = {2021},\n    month = {08},\n    issn = {0360-3989},\n    doi = {10.1093/hcr/hqab009},\n    url = {https://doi.org/10.1093/hcr/hqab009},\n    keywords = {social media},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n SemEval-2021 Task 10: Source-Free Domain Adaptation for Semantic Processing.\n \n \n \n \n\n\n \n Egoitz Laparra; Xin Su; Yiyun Zhao; Özlem Uzuner; Timothy Miller; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 348–356, Online, August 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"SemEval-2021Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{laparra-etal-2021-semeval,\n    title = "{S}em{E}val-2021 Task 10: Source-Free Domain Adaptation for Semantic Processing",\n    author = {Laparra, Egoitz  and\n      Su, Xin  and\n      Zhao, Yiyun  and\n      Uzuner, {\\"O}zlem  and\n      Miller, Timothy  and\n      Bethard, Steven},\n    booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",\n    month = aug,\n    year = "2021",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2021.semeval-1.42",\n    doi = "10.18653/v1/2021.semeval-1.42",\n    pages = "348--356",\n    keywords = {domain adaptation, negation, timelines, information extraction, health applications, shared task paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation.\n \n \n \n \n\n\n \n Xin Su; Yiyun Zhao; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 458–466, Online, August 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ThePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{su-etal-2021-university,\n    title = "The {U}niversity of {A}rizona at {S}em{E}val-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation",\n    author = "Su, Xin  and\n      Zhao, Yiyun  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",\n    month = aug,\n    year = "2021",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://aclanthology.org/2021.semeval-1.56",\n    doi = "10.18653/v1/2021.semeval-1.56",\n    pages = "458--466",\n    keywords = {domain adaptation, negation, timelines, information extraction, health applications, shared task paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization.\n \n \n \n \n\n\n \n Dongfang Xu; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 11–22, Online, June 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Triplet-TrainedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 19 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{xu-bethard-2021-triplet,\n    title = "Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization",\n    author = "Xu, Dongfang  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",\n    month = jun,\n    year = "2021",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2021.bionlp-1.2",\n    pages = "11--22",\n    keywords = {term normalization, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n EntityBERT: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain.\n \n \n \n \n\n\n \n Chen Lin; Timothy Miller; Dmitriy Dligach; Steven Bethard; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 191–201, Online, June 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"EntityBERT:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 9 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{lin-etal-2021-entitybert,\n    title = "{E}ntity{BERT}: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain",\n    author = "Lin, Chen  and\n      Miller, Timothy  and\n      Dligach, Dmitriy  and\n      Bethard, Steven  and\n      Savova, Guergana",\n    booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",\n    month = jun,\n    year = "2021",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2021.bionlp-1.21",\n    pages = "191--201",\n    keywords = {timelines, information extraction, health applications, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Explainable Multi-hop Verbal Reasoning Through Internal Monologue.\n \n \n \n \n\n\n \n Zhengzhong Liang; Steven Bethard; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1225–1250, Online, June 2021. Association for Computational Linguistics\n [Acceptance rate 26%]\n\n\n\n
\n\n\n\n \n \n \"ExplainablePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 58 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{liang-etal-2021-explainable,\n    title = "Explainable Multi-hop Verbal Reasoning Through Internal Monologue",\n    author = "Liang, Zhengzhong  and\n      Bethard, Steven  and\n      Surdeanu, Mihai",\n    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",\n    month = jun,\n    year = "2021",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2021.naacl-main.97",\n    pages = "1225--1250",\n    note = {[Acceptance rate 26\\%]},\n    keywords = {question answering},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering.\n \n \n \n \n\n\n \n Vikas Yadav; Steven Bethard; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4571–4581, Online, June 2021. Association for Computational Linguistics\n [Acceptance rate 26%]\n\n\n\n
\n\n\n\n \n \n \"IfPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 23 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{yadav-etal-2021-want,\n    title = "If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering",\n    author = "Yadav, Vikas  and\n      Bethard, Steven  and\n      Surdeanu, Mihai",\n    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",\n    month = jun,\n    year = "2021",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2021.naacl-main.363",\n    pages = "4571--4581",\n    note = {[Acceptance rate 26\\%]},\n    keywords = {question answering},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.\n \n \n \n \n\n\n \n Kristina Toutanova; Anna Rumshisky; Luke Zettlemoyer; Dilek Hakkani-Tur; Iz Beltagy; Steven Bethard; Ryan Cotterell; Tanmoy Chakraborty; and Yichao Zhou.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. Online, June 2021.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 10 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@proceedings{naacl-2021-2021,\n    title = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",\n    editor = "Toutanova, Kristina  and\n      Rumshisky, Anna  and\n      Zettlemoyer, Luke  and\n      Hakkani-Tur, Dilek  and\n      Beltagy, Iz  and\n      Bethard, Steven  and\n      Cotterell, Ryan  and\n      Chakraborty, Tanmoy  and\n      Zhou, Yichao",\n    month = jun,\n    year = "2021",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2021.naacl-main.0",\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Domain adaptation in practice: Lessons from a real-world information extraction pipeline.\n \n \n \n \n\n\n \n Timothy Miller; Egoitz Laparra; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the Second Workshop on Domain Adaptation for NLP, pages 105–110, Kyiv, Ukraine, April 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"DomainPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{miller-etal-2021-domain,\n    title = "Domain adaptation in practice: Lessons from a real-world information extraction pipeline",\n    author = "Miller, Timothy  and\n      Laparra, Egoitz  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the Second Workshop on Domain Adaptation for NLP",\n    month = apr,\n    year = "2021",\n    address = "Kyiv, Ukraine",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2021.adaptnlp-1.11",\n    pages = "105--110",\n    keywords = {domain adaptation, information extraction, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Consumer Cynicism Identification for Spanish Reviews using a Spanish Transformer Model.\n \n \n \n \n\n\n \n Samuel González-López; Steven Bethard; Francisca Cecilia Encinas Orozco; and Adriıan Pastor López-Monroy.\n\n\n \n\n\n\n Procesamiento del Lenguaje Natural, 66(0): 111–120. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"ConsumerPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@article{gonzalez-lopez-2021-PLN,\n\tauthor = {Samuel Gonz\\'{a}lez-L\\'{o}pez and Steven Bethard and Francisca Cecilia Encinas Orozco and Adri\\i{a}n Pastor L\\'{o}pez-Monroy},\n\ttitle = {Consumer Cynicism Identification for Spanish Reviews using a Spanish Transformer Model},\n\tjournal = {Procesamiento del Lenguaje Natural},\n\tvolume = {66},\n\tnumber = {0},\n\tyear = {2021},\n\tissn = {1989-7553},\n\turl = {http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6327},\n\tpages = {111--120},\n\tkeywords = {social media},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2020\n \n \n (22)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios.\n \n \n \n \n\n\n \n Andrew Zupon; Faiz Rafique; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Workshop on Insights from Negative Results in NLP, 2020. \n \n\n\n\n
\n\n\n\n \n \n \"AnPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 10 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{zupon2020capsnet,\n  title={An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios},\n  author={Zupon, Andrew and Rafique, Faiz and Surdeanu, Mihai},\n  booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Workshop on Insights from Negative Results in NLP},\n  url={http://clulab.org/papers/insights2020-capsnet.pdf},\n  year={2020}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Do Transformers Dream of Inference, or Can Pretrained Generative Models Learn Implicit Inferential Rules?.\n \n \n \n \n\n\n \n Zhengzhong Liang; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Workshop on Insights from Negative Results in NLP, 2020. \n \n\n\n\n
\n\n\n\n \n \n \"DoPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 16 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{liang2020can,\n  title={Do Transformers Dream of Inference, or Can Pretrained Generative Models Learn Implicit Inferential Rules?},\n  author={Liang, Zhengzhong and Surdeanu, Mihai},\n  booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Workshop on Insights from Negative Results in NLP},\n  url={http://clulab.org/papers/emnlp2020-can.pdf},\n  year={2020}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n The Language of Food during the Pandemic: Hints about the Dietary Effects of Covid-19.\n \n \n \n \n\n\n \n Hoang Van; Ahmad Musa; Mihai Surdeanu; and Stephen Kobourov.\n\n\n \n\n\n\n arXiv preprint arXiv:2010.07466. 2020.\n \n\n\n\n
\n\n\n\n \n \n \"ThePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 20 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{van2020covid,\n  title={The Language of Food during the Pandemic: Hints about the Dietary Effects of Covid-19},\n  author={Hoang Van and Ahmad Musa and Mihai Surdeanu and Stephen Kobourov},\n  journal={arXiv preprint arXiv:2010.07466},\n  url={https://arxiv.org/abs/2010.07466},\n  year={2020}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering.\n \n \n \n \n\n\n \n Zhengzhong Liang; Yiyun Zhao; and Mihai Surdeanu.\n\n\n \n\n\n\n arXiv preprint arXiv:2009.10791. 2020.\n \n\n\n\n
\n\n\n\n \n \n \"UsingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 11 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{liang2020using,\n  title={Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering},\n  author={Liang, Zhengzhong and Zhao, Yiyun and Surdeanu, Mihai},\n  journal={arXiv preprint arXiv:2009.10791},\n  url = "https://arxiv.org/abs/2009.10791",\n  year={2020}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Parsing as Tagging.\n \n \n \n \n\n\n \n Robert Vacareanu; George C. G. Barbosa; Marco A. Valenzuela-Escarcega; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC), 2020. \n \n\n\n\n
\n\n\n\n \n \n \"ParsingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 31 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{vacareanu2020parsing,\n    author = {Robert Vacareanu and George C. G. Barbosa and Marco A. Valenzuela-Escarcega and Mihai Surdeanu},\n    title = {Parsing as Tagging},\n    booktitle = {Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC)},\n    year = {2020},\n    url = {http://clulab.org/papers/pat.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder.\n \n \n \n \n\n\n \n Zheng Tang; Gustave Hahn-Powell; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, Seattle, United States, July 2020. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ExploringPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 26 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{zheng-tang-2019-edin,\n    title = "Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder",\n    author = "Tang, Zheng and Hahn-Powell, Gustave and Surdeanu, Mihai",\n    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",\n    month = jul,\n    year = "2020",\n    address = "Seattle, United States",\n    publisher = "Association for Computational Linguistics",\n    url = "http://clulab.org/papers/aclsrw2020-edin.pdf"\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification.\n \n \n \n \n\n\n \n Robert Vacareanu; Marco A. Valenzuela-Escarcega; Rebecca Sharp; and Mihai Surdeanu.\n\n\n \n\n\n\n In The 28th International Conference on Computational Linguistics in Barcelona (COLING 2020), 2020. \n \n\n\n\n
\n\n\n\n \n \n \"AnPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 8 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{vacareanu2020mwe,\n  title={An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification},\n  author={Robert Vacareanu and Marco A. Valenzuela-Escarcega and Rebecca Sharp and Mihai Surdeanu},\n  booktitle={The 28th International Conference on Computational Linguistics in Barcelona (COLING 2020)},\n  url={http://clulab.org/papers/coling2020-mwe.pdf},\n  year={2020}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n MathAlign: Linking Formula Identifiers to their Contextual Natural Language Descriptions.\n \n \n \n \n\n\n \n Maria Alexeeva; Rebecca Sharp; Marco A. Valenzuela-Escárcega; Jennifer Kadowaki; Adarsh Pyarelal; and Clayton Morrison.\n\n\n \n\n\n\n In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 2204–2212, Marseille, France, May 2020. European Language Resources Association\n \n\n\n\n
\n\n\n\n \n \n \"MathAlign:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{alexeeva-etal-2020-mathalign,\n    title = "{M}ath{A}lign: Linking Formula Identifiers to their Contextual Natural Language Descriptions",\n    author = "Alexeeva, Maria  and\n      Sharp, Rebecca  and\n      Valenzuela-Esc{\\'a}rcega, Marco A.  and\n      Kadowaki, Jennifer  and\n      Pyarelal, Adarsh  and\n      Morrison, Clayton",\n    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",\n    month = may,\n    year = "2020",\n    address = "Marseille, France",\n    publisher = "European Language Resources Association",\n    url = "https://aclanthology.org/2020.lrec-1.269",\n    pages = "2204--2212",\n    abstract = "Extending machine reading approaches to extract mathematical concepts and their descriptions is useful for a variety of tasks, ranging from mathematical information retrieval to increasing accessibility of scientific documents for the visually impaired. This entails segmenting mathematical formulae into identifiers and linking them to their natural language descriptions. We propose a rule-based approach for this task, which extracts LaTeX representations of formula identifiers and links them to their in-text descriptions, given only the original PDF and the location of the formula of interest. We also present a novel evaluation dataset for this task, as well as the tool used to create it.",\n    language = "English",\n    ISBN = "979-10-95546-34-4",\n}\n
\n
\n\n\n
\n Extending machine reading approaches to extract mathematical concepts and their descriptions is useful for a variety of tasks, ranging from mathematical information retrieval to increasing accessibility of scientific documents for the visually impaired. This entails segmenting mathematical formulae into identifiers and linking them to their natural language descriptions. We propose a rule-based approach for this task, which extracts LaTeX representations of formula identifiers and links them to their in-text descriptions, given only the original PDF and the location of the formula of interest. We also present a novel evaluation dataset for this task, as well as the tool used to create it.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n TTUI at SemEval-2020 Task 11: Propaganda Detection with Transfer Learning and Ensembles.\n \n \n \n \n\n\n \n Moonsung Kim; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1829–1834, Barcelona (online), December 2020. International Committee for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"TTUIPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 11 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{kim-bethard-2020-ttui,\n    title = "{TTUI} at {S}em{E}val-2020 Task 11: Propaganda Detection with Transfer Learning and Ensembles",\n    author = "Kim, Moonsung  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",\n    month = dec,\n    year = "2020",\n    address = "Barcelona (online)",\n    publisher = "International Committee for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2020.semeval-1.240",\n    pages = "1829--1834",\n    keywords = {shared task paper, social media},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Dataset and Evaluation Framework for Complex Geographical Description Parsing.\n \n \n \n \n\n\n \n Egoitz Laparra; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 28th International Conference on Computational Linguistics, pages 936–948, Barcelona, Spain (Online), December 2020. International Committee on Computational Linguistics\n [Acceptance rate 35%]\n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 20 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{laparra-bethard-2020-dataset,\n    title = "A Dataset and Evaluation Framework for Complex Geographical Description Parsing",\n    author = "Laparra, Egoitz  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",\n    month = dec,\n    year = "2020",\n    address = "Barcelona, Spain (Online)",\n    publisher = "International Committee on Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2020.coling-main.81",\n    pages = "936--948",\n    keywords = {locations, information extraction},\n    note = {[Acceptance rate 35\\%]},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of the 3rd Clinical Natural Language Processing Workshop.\n \n \n \n \n\n\n \n Anna Rumshisky; Kirk Roberts; Steven Bethard; and Tristan Naumann.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. Online, November 2020.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 7 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@proceedings{clinicalnlp-2020-clinical,\n    title = "Proceedings of the 3rd Clinical Natural Language Processing Workshop",\n    editor = "Rumshisky, Anna  and\n      Roberts, Kirk  and\n      Bethard, Steven  and\n      Naumann, Tristan",\n    month = nov,\n    year = "2020",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2020.clinicalnlp-1.0",\n    keywords = {health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Defining and Learning Refined Temporal Relations in the Clinical Narrative.\n \n \n \n \n\n\n \n Kristin Wright-Bettner; Chen Lin; Timothy Miller; Steven Bethard; Dmitriy Dligach; Martha Palmer; James H. Martin; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis, pages 104–114, Online, November 2020. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"DefiningPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{wright-bettner-etal-2020-defining,\n    title = "Defining and Learning Refined Temporal Relations in the Clinical Narrative",\n    author = "Wright-Bettner, Kristin  and\n      Lin, Chen  and\n      Miller, Timothy  and\n      Bethard, Steven  and\n      Dligach, Dmitriy  and\n      Palmer, Martha  and\n      Martin, James H.  and\n      Savova, Guergana",\n    booktitle = "Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis",\n    month = nov,\n    year = "2020",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2020.louhi-1.12",\n    doi = "10.18653/v1/2020.louhi-1.12",\n    pages = "104--114",\n    keywords = {annotation, timelines, information extraction, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Fine-tuning for multi-domain and multi-label uncivil language detection.\n \n \n \n \n\n\n \n Kadir Bulut Ozler; Kate Kenski; Steve Rains; Yotam Shmargad; Kevin Coe; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the Fourth Workshop on Online Abuse and Harms, pages 28–33, Online, November 2020. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Fine-tuningPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{ozler-etal-2020-fine,\n    title = "Fine-tuning for multi-domain and multi-label uncivil language detection",\n    author = "Ozler, Kadir Bulut  and\n      Kenski, Kate  and\n      Rains, Steve  and\n      Shmargad, Yotam  and\n      Coe, Kevin  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the Fourth Workshop on Online Abuse and Harms",\n    month = nov,\n    year = "2020",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2020.alw-1.4",\n    doi = "10.18653/v1/2020.alw-1.4",\n    pages = "28--33",\n    keywords = {social media, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Having Your Cake and Eating It Too: Training Neural Retrieval for Language Inference without Losing Lexical Match.\n \n \n \n \n\n\n \n Vikas Yadav; Steven Bethard; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, of SIGIR '20, pages 1625–1628, New York, NY, USA, 7 2020. Association for Computing Machinery\n [Acceptance rate 26%]\n\n\n\n
\n\n\n\n \n \n \"HavingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 16 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{10.1145/3397271.3401311,\nauthor = {Yadav, Vikas and Bethard, Steven and Surdeanu, Mihai},\ntitle = {Having Your Cake and Eating It Too: Training Neural Retrieval for Language Inference without Losing Lexical Match},\nyear = {2020},\nmonth = {7},\nisbn = {9781450380164},\npublisher = {Association for Computing Machinery},\naddress = {New York, NY, USA},\nurl = {https://doi.org/10.1145/3397271.3401311},\ndoi = {10.1145/3397271.3401311},\nbooktitle = {Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval},\npages = {1625--1628},\nnumpages = {4},\nlocation = {Virtual Event, China},\nseries = {SIGIR '20},\nkeywords = {question answering},\nnote = {[Acceptance rate 26\\%]},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Unified Medical Language System resources improve sieve-based generation and Bidirectional Encoder Representations from Transformers (BERT)-based ranking for concept normalization.\n \n \n \n \n\n\n \n Dongfang Xu; Manoj Gopale; Jiacheng Zhang; Kris Brown; Edmon Begoli; and Steven Bethard.\n\n\n \n\n\n\n Journal of the American Medical Informatics Association. 07 2020.\n \n\n\n\n
\n\n\n\n \n \n \"UnifiedPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 7 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@article{xu-etal-2020-unified,\n    author = {Xu, Dongfang and Gopale, Manoj and Zhang, Jiacheng and Brown, Kris and Begoli, Edmon and Bethard, Steven},\n    title = {Unified Medical Language System resources improve sieve-based generation and Bidirectional Encoder Representations from Transformers (BERT)-based ranking for concept normalization},\n    journal = {Journal of the American Medical Informatics Association},\n    year = {2020},\n    month = {07},\n    issn = {1527-974X},\n    doi = {10.1093/jamia/ocaa080},\n    url = {https://doi.org/10.1093/jamia/ocaa080},\n    keywords = {health applications, term normalization},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A BERT-based One-Pass Multi-Task Model for Clinical Temporal Relation Extraction.\n \n \n \n \n\n\n \n Chen Lin; Timothy Miller; Dmitriy Dligach; Farig Sadeque; Steven Bethard; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing, pages 70–75, Online, July 2020. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{lin-etal-2020-bert,\n    title = "A {BERT}-based One-Pass Multi-Task Model for Clinical Temporal Relation Extraction",\n    author = "Lin, Chen  and\n      Miller, Timothy  and\n      Dligach, Dmitriy  and\n      Sadeque, Farig  and\n      Bethard, Steven  and\n      Savova, Guergana",\n    booktitle = "Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing",\n    month = jul,\n    year = "2020",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2020.bionlp-1.7",\n    pages = "70--75",\n    keywords = {workshop paper, health applications, timelines, information extraction},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Assisting Undergraduate Students in Writing Spanish Methodology Sections.\n \n \n \n \n\n\n \n Samuel González-López; Steven Bethard; and Aurelio Lopez-Lopez.\n\n\n \n\n\n\n In Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 115–123, Seattle, WA, USA - Online, July 2020. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"AssistingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{gonzalez-lopez-etal-2020-assisting,\n    title = "Assisting Undergraduate Students in Writing {S}panish Methodology Sections",\n    author = "Gonz{\\'a}lez-L{\\'o}pez, Samuel  and\n      Bethard, Steven  and\n      Lopez-Lopez, Aurelio",\n    booktitle = "Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications",\n    month = jul,\n    year = "2020",\n    address = "Seattle, WA, USA - Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2020.bea-1.11",\n    pages = "115--123",\n    keywords = {educational applications, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Generate-and-Rank Framework with Semantic Type Regularization for Biomedical Concept Normalization.\n \n \n \n \n\n\n \n Dongfang Xu; Zeyu Zhang; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8452–8464, Online, July 2020. Association for Computational Linguistics\n [Acceptance rate 23%]\n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 8 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{xu-etal-2020-generate,\n    title = "A Generate-and-Rank Framework with Semantic Type Regularization for Biomedical Concept Normalization",\n    author = "Xu, Dongfang  and\n      Zhang, Zeyu  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",\n    month = jul,\n    year = "2020",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2020.acl-main.748",\n    pages = "8452--8464",\n    note = {[Acceptance rate 23\\%]},\n    keywords = {health applications, term normalization},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n How does BERT's attention change when you fine-tune? An analysis methodology and a case study in negation scope.\n \n \n \n \n\n\n \n Yiyun Zhao; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4729–4747, Online, July 2020. Association for Computational Linguistics\n [Acceptance rate 23%]\n\n\n\n
\n\n\n\n \n \n \"HowPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 6 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{zhao-bethard-2020-berts,\n    title = "How does {BERT}{'}s attention change when you fine-tune? An analysis methodology and a case study in negation scope",\n    author = "Zhao, Yiyun  and\n      Bethard, Steven",\n    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",\n    month = jul,\n    year = "2020",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2020.acl-main.429",\n    pages = "4729--4747",\n    note = {[Acceptance rate 23\\%]},\n    keywords = {negation, machine learning},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering.\n \n \n \n \n\n\n \n Vikas Yadav; Steven Bethard; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4514–4525, Online, July 2020. Association for Computational Linguistics\n [Acceptance rate 23%]\n\n\n\n
\n\n\n\n \n \n \"UnsupervisedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 31 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{yadav-etal-2020-unsupervised,\n    title = "Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering",\n    author = "Yadav, Vikas  and\n      Bethard, Steven  and\n      Surdeanu, Mihai",\n    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",\n    month = jul,\n    year = "2020",\n    address = "Online",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/2020.acl-main.414",\n    pages = "4514--4525",\n    note = {[Acceptance rate 23\\%]},\n    keywords = {question answering},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Rethinking domain adaptation for machine learning over clinical language.\n \n \n \n \n\n\n \n Egoitz Laparra; Steven Bethard; and Timothy A Miller.\n\n\n \n\n\n\n JAMIA Open. 04 2020.\n \n\n\n\n
\n\n\n\n \n \n \"RethinkingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@article{laparra-bethard-miller:2020:JAMIAOpen,\n    author = {Laparra, Egoitz and Bethard, Steven and Miller, Timothy A},\n    title = "{Rethinking domain adaptation for machine learning over clinical language}",\n    journal = {JAMIA Open},\n    year = {2020},\n    month = {04},\n    issn = {2574-2531},\n    doi = {10.1093/jamiaopen/ooaa010},\n    url = {https://doi.org/10.1093/jamiaopen/ooaa010},\n    keywords = {domain adaptation, health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Does BERT need domain adaptation for clinical negation detection?.\n \n \n \n \n\n\n \n Chen Lin; Steven Bethard; Dmitriy Dligach; Farig Sadeque; Guergana Savova; and Timothy A Miller.\n\n\n \n\n\n\n Journal of the American Medical Informatics Association, 27(4): 584-591. 02 2020.\n \n\n\n\n
\n\n\n\n \n \n \"DoesPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@article{chen-etal:2020:JAMIA,\n    author = {Lin, Chen and Bethard, Steven and Dligach, Dmitriy and Sadeque, Farig and Savova, Guergana and Miller, Timothy A},\n    title = "{Does BERT need domain adaptation for clinical negation detection?}",\n    journal = {Journal of the American Medical Informatics Association},\n    volume = {27},\n    number = {4},\n    pages = {584-591},\n    year = {2020},\n    month = {02},\n    issn = {1527-974X},\n    doi = {10.1093/jamia/ocaa001},\n    url = {https://doi.org/10.1093/jamia/ocaa001},\n    keywords = {negation, health applications},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2019\n \n \n (16)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text.\n \n \n \n \n\n\n \n George C.G. Barbosa; Zechy Wong; Gus Hahn-Powell; Dane Bell; Rebecca Sharp; Marco A. Valenzuela-Escarcega; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT): Software Demonstrations, 2019. \n This paper received the Best System Demonstration award\n\n\n\n
\n\n\n\n \n \n \"EnablingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 11 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{barbosa2019,\n    title={Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text},\n    author={Barbosa, George C.G. and Wong, Zechy and Hahn-Powell, Gus and Bell, Dane and Sharp, Rebecca and Valenzuela-Escarcega, Marco A. and Surdeanu, Mihai},\n    booktitle={Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT): Software Demonstrations},\n    year={2019},\n    note={This paper received the Best System Demonstration award},\n    url={http://clulab.org/papers/NAACL2019_1.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Understanding the Polarity of Events in the Biomedical Literature: Deep Learning vs. Linguistically-informed Methods.\n \n \n \n \n\n\n \n Enrique Noriega-Atala; Zhengzhong Liang; John A. Bachman; Clayton T. Morrison; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications, 2019. NAACL-HLT\n \n\n\n\n
\n\n\n\n \n \n \"UnderstandingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@INPROCEEDINGS {polarity2019,\n    author    = "Enrique Noriega-Atala and Zhengzhong Liang and John A. Bachman and Clayton T. Morrison and Mihai Surdeanu",\n    title     = "Understanding the Polarity of Events in the Biomedical Literature: Deep Learning vs. Linguistically-informed Methods",\n    booktitle = "Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications",\n    organization={NAACL-HLT},\n    year      = "2019",\n    url = {http://clulab.org/papers/polarity19.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Semi-Supervised Teacher-Student Architecture for Relation Extraction.\n \n \n \n \n\n\n \n Fan Luo; Ajay Nagesh; Rebecca Sharp; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 3rd Workshop on Structured Prediction for Natural Language Processing, 2019. NAACL-HLT\n \n\n\n\n
\n\n\n\n \n \n \"Semi-SupervisedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{fan2019MTre,\ntitle={Semi-Supervised Teacher-Student Architecture for Relation Extraction},\nauthor={Fan Luo and\nAjay Nagesh and\nRebecca Sharp and\nMihai Surdeanu},\nbooktitle = {Proceedings of the 3rd Workshop on Structured Prediction for Natural Language Processing},\nyear={2019},\norganization={NAACL-HLT},\nurl={http://clulab.org/papers/meanteacherre19.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Lightly Supervised Representation Learning with Global Interpretability.\n \n \n \n \n\n\n \n Andrew Zupon; Maria Alexeeva; Marco A. Valenzuela-Escarcega; Ajay Nagesh; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 3rd Workshop on Structured Prediction for Natural Language Processing, 2019. NAACL-HLT\n \n\n\n\n
\n\n\n\n \n \n \"LightlyPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@INPROCEEDINGS {naaclhlt2019-emboot,\n    author       = "Andrew Zupon and Maria Alexeeva and Marco A. Valenzuela-Escarcega and Ajay Nagesh and Mihai Surdeanu",\n    title        = "Lightly Supervised Representation Learning with Global Interpretability",\n    booktitle    = "Proceedings of the 3rd Workshop on Structured Prediction for Natural Language Processing",\n    year         = "2019",\n    organization = "NAACL-HLT",\n    url = {http://clulab.org/papers/naaclhlt2019-emboot.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n What does the language of foods say about us?.\n \n \n \n \n\n\n \n Hoang Van; Ahmad Musa; Hang Chen; Mihai Surdeanu; and Stephen Kobourov.\n\n\n \n\n\n\n In Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI), 2019. \n \n\n\n\n
\n\n\n\n \n \n \"WhatPaper\n  \n \n \n \"What slides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{van2019language,\n  title\t    = {What does the language of foods say about us?},\n  author    = {Van, Hoang and Musa, Ahmad and Chen, Hang and Surdeanu, Mihai and Kobourov, Stephen},\n  booktitle = {Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI)},\n  year      = {2019},\n  url = {http://clulab.org/papers/louhi2019.pdf},\n  url_Slides = {http://clulab.org/papers/louhi2019.pptx}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n On the Importance of Delexicalization for Fact Verification.\n \n \n \n \n\n\n \n Sandeep Suntwal; Mithun Paul; Rebecca Sharp; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3413-3418, Hong Kong, China, November 2019. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"OnPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 10 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{suntwal-etal-2019-importance,\n    title = "On the Importance of Delexicalization for Fact Verification",\n    author = "Suntwal, Sandeep  and\n      Paul, Mithun  and\n      Sharp, Rebecca  and\n      Surdeanu, Mihai",\n    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",\n    month = nov,\n    year = "2019",\n    address = "Hong Kong, China",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/D19-1340",\n    doi = "10.18653/v1/D19-1340",\n    pages = "3413-3418",\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering.\n \n \n \n \n\n\n \n Vikas Yadav; Steven Bethard; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2578–2589, Hong Kong, China, November 2019. Association for Computational Linguistics\n [Acceptance rate 23%]\n\n\n\n
\n\n\n\n \n \n \"QuickPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 7 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{yadav-etal-2019-quick,\n    title = "Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering",\n    author = "Yadav, Vikas  and\n      Bethard, Steven  and\n      Surdeanu, Mihai",\n    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",\n    month = nov,\n    year = "2019",\n    address = "Hong Kong, China",\n    publisher = "Association for Computational Linguistics",\n    url = "https://www.aclweb.org/anthology/D19-1260",\n    doi = "10.18653/v1/D19-1260",\n    pages = "2578--2589",\n    note = {[Acceptance rate 23\\%]},\n    keywords = {question answering},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of the 2nd Clinical Natural Language Processing Workshop.\n \n \n \n \n\n\n \n Anna Rumshisky; Kirk Roberts; Steven Bethard; and Tristan Naumann.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. Minneapolis, Minnesota, USA, 6 2019.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@proceedings{W19-19:2019,\n  editor    = {Anna Rumshisky  and  Kirk Roberts  and  Steven Bethard  and  Tristan Naumann},\n  title     = {Proceedings of the 2nd Clinical Natural Language Processing Workshop},\n  month     = {6},\n  year      = {2019},\n  address   = {Minneapolis, Minnesota, USA},\n  publisher = {Association for Computational Linguistics},\n  url       = {http://www.aclweb.org/anthology/W19-19},\n  keywords = {health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Inferring missing metadata from environmental policy texts.\n \n \n \n \n\n\n \n Steven Bethard; Egoitz Laparra; Sophia Wang; Yiyun Zhao; Ragheb Al-Ghezi; Aaron Lien; and Laura López-Hoffman.\n\n\n \n\n\n\n In Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 46–51, Minneapolis, USA, 6 2019. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"InferringPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{bethard-EtAl:2019:W19-25,\n  author    = {Bethard, Steven  and  Laparra, Egoitz  and  Wang, Sophia  and  Zhao, Yiyun  and  Al-Ghezi, Ragheb  and  Lien, Aaron  and  L\\'{o}pez-Hoffman, Laura},\n  title     = {Inferring missing metadata from environmental policy texts},\n  booktitle = {Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature},\n  month     = {6},\n  year      = {2019},\n  address   = {Minneapolis, USA},\n  publisher = {Association for Computational Linguistics},\n  pages     = {46--51},\n  url       = {http://www.aclweb.org/anthology/W19-2506},\n  keywords = {workshop paper, environmental policy},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A BERT-based Universal Model for Both Within- and Cross-sentence Clinical Temporal Relation Extraction.\n \n \n \n \n\n\n \n Chen Lin; Timothy Miller; Dmitriy Dligach; Steven Bethard; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the 2nd Clinical Natural Language Processing Workshop, pages 65–71, Minneapolis, Minnesota, USA, 6 2019. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{lin-EtAl:2019:W19-19,\n  author    = {Lin, Chen  and  Miller, Timothy  and  Dligach, Dmitriy  and  Bethard, Steven  and  Savova, Guergana},\n  title     = {A BERT-based Universal Model for Both Within- and Cross-sentence Clinical Temporal Relation Extraction},\n  booktitle = {Proceedings of the 2nd Clinical Natural Language Processing Workshop},\n  month     = {6},\n  year      = {2019},\n  address   = {Minneapolis, Minnesota, USA},\n  publisher = {Association for Computational Linguistics},\n  pages     = {65--71},\n  url       = {http://www.aclweb.org/anthology/W19-1908},\n  keywords = {workshop paper, health applications, timelines, information extraction},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n University of Arizona at SemEval-2019 Task 12: Deep-Affix Named Entity Recognition of Geolocation Entities.\n \n \n \n \n\n\n \n Vikas Yadav; Egoitz Laparra; Ti-Tai Wang; Mihai Surdeanu; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 1319–1323, Minneapolis, Minnesota, USA, 6 2019. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"UniversityPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{yadav-EtAl:2019:S19-2,\n  author    = {Yadav, Vikas  and  Laparra, Egoitz  and  Wang, Ti-Tai  and  Surdeanu, Mihai  and  Bethard, Steven},\n  title     = {University of Arizona at SemEval-2019 Task 12: Deep-Affix Named Entity Recognition of Geolocation Entities},\n  booktitle = {Proceedings of the 13th International Workshop on Semantic Evaluation},\n  month     = {6},\n  year      = {2019},\n  address   = {Minneapolis, Minnesota, USA},\n  publisher = {Association for Computational Linguistics},\n  pages     = {1319--1323},\n  url       = {http://www.aclweb.org/anthology/S19-2232},\n  keywords = {shared task paper, locations, information extraction},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Incivility Detection in Online Comments.\n \n \n \n \n\n\n \n Farig Sadeque; Stephen Rains; Yotam Shmargad; Kate Kenski; Kevin Coe; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pages 283–291, Minneapolis, Minnesota, 6 2019. Association for Computational Linguistics\n [Acceptance rate 33%]\n\n\n\n
\n\n\n\n \n \n \"IncivilityPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{sadeque-EtAl:2019:S19-1,\n  author    = {Sadeque, Farig  and  Rains, Stephen  and  Shmargad, Yotam  and  Kenski, Kate  and  Coe, Kevin  and  Bethard, Steven},\n  title     = {Incivility Detection in Online Comments},\n  booktitle = {Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)},\n  month     = {6},\n  year      = {2019},\n  address   = {Minneapolis, Minnesota},\n  publisher = {Association for Computational Linguistics},\n  pages     = {283--291},\n  url       = {http://www.aclweb.org/anthology/S19-1031},\n  note = {[Acceptance rate 33\\%]},\n  keywords = {social media},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Pre-trained Contextualized Character Embeddings Lead to Major Improvements in Time Normalization: a Detailed Analysis.\n \n \n \n \n\n\n \n Dongfang Xu; Egoitz Laparra; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pages 68–74, Minneapolis, Minnesota, 6 2019. Association for Computational Linguistics\n [Acceptance rate 33%]\n\n\n\n
\n\n\n\n \n \n \"Pre-trainedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 18 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{xu-laparra-bethard:2019:S19-1,\n  author    = {Xu, Dongfang  and  Laparra, Egoitz  and  Bethard, Steven},\n  title     = {Pre-trained Contextualized Character Embeddings Lead to Major Improvements in Time Normalization: a Detailed Analysis},\n  booktitle = {Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)},\n  month     = {6},\n  year      = {2019},\n  address   = {Minneapolis, Minnesota},\n  publisher = {Association for Computational Linguistics},\n  pages     = {68--74},\n  url       = {http://www.aclweb.org/anthology/S19-1008},\n  note = {[Acceptance rate 33\\%]},\n  keywords = {timelines, information extraction},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Eidos, INDRA, & Delphi: From Free Text to Executable Causal Models.\n \n \n \n \n\n\n \n Rebecca Sharp; Adarsh Pyarelal; Benjamin Gyori; Keith Alcock; Egoitz Laparra; Marco A. Valenzuela-Escárcega; Ajay Nagesh; Vikas Yadav; John Bachman; Zheng Tang; Heather Lent; Fan Luo; Mithun Paul; Steven Bethard; Kobus Barnard; Clayton Morrison; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pages 42–47, Minneapolis, Minnesota, 6 2019. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Eidos,Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 7 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{sharp-EtAl:2019:N19-4,\n  author    = {Sharp, Rebecca  and  Pyarelal, Adarsh  and  Gyori, Benjamin  and  Alcock, Keith  and  Laparra, Egoitz  and  Valenzuela-Esc\\'{a}rcega, Marco A.  and  Nagesh, Ajay  and  Yadav, Vikas  and  Bachman, John  and  Tang, Zheng  and  Lent, Heather  and  Luo, Fan  and  Paul, Mithun  and  Bethard, Steven  and  Barnard, Kobus  and  Morrison, Clayton  and  Surdeanu, Mihai},\n  title     = {Eidos, INDRA, \\& Delphi: From Free Text to Executable Causal Models},\n  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)},\n  month     = {6},\n  year      = {2019},\n  address   = {Minneapolis, Minnesota},\n  publisher = {Association for Computational Linguistics},\n  pages     = {42--47},\n  url       = {http://www.aclweb.org/anthology/N19-4008},\n  keywords = {demo paper, causal relations, timelines, locations, information extraction},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Alignment over Heterogeneous Embeddings for Question Answering.\n \n \n \n \n\n\n \n Vikas Yadav; Steven Bethard; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2681–2691, Minneapolis, Minnesota, 6 2019. Association for Computational Linguistics\n [Acceptance rate 26%]\n\n\n\n
\n\n\n\n \n \n \"AlignmentPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 8 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{yadav-bethard-surdeanu:2019:N19-1,\n  author    = {Yadav, Vikas  and  Bethard, Steven  and  Surdeanu, Mihai},\n  title     = {Alignment over Heterogeneous Embeddings for Question Answering},\n  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)},\n  month     = {6},\n  year      = {2019},\n  address   = {Minneapolis, Minnesota},\n  publisher = {Association for Computational Linguistics},\n  pages     = {2681--2691},\n  url       = {http://www.aclweb.org/anthology/N19-1274},\n  note = {[Acceptance rate 26\\%]},\n  keywords = {question answering},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Model for Identifying Steps in Undergraduate Thesis Methodology.\n \n \n \n \n\n\n \n Samuel González López; Aurelio López-López; Steven Bethard; and Jesús Miguel García Gorrostieta.\n\n\n \n\n\n\n Res. Comput. Sci., 148(5): 17–24. 2019.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@article{gonzalez-lopez-EtAl:2019:RCS,\n  author    = {Samuel Gonz{\\'{a}}lez L{\\'{o}}pez and\n               Aurelio L{\\'{o}}pez{-}L{\\'{o}}pez and\n               Steven Bethard and\n               Jes{\\'{u}}s Miguel Garc{\\'{i}}a Gorrostieta},\n  title     = {A Model for Identifying Steps in Undergraduate Thesis Methodology},\n  journal   = {Res. Comput. Sci.},\n  volume    = {148},\n  number    = {5},\n  pages     = {17--24},\n  year      = {2019},\n  url       = {http://rcs.cic.ipn.mx/2019\\_148\\_5/A\\%20Model\\%20for\\%20Identifying\\%20Steps\\%20in\\%20Undergraduate\\%20Thesis\\%20Methodology.pdf},\n  keywords = {educational applications},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2018\n \n \n (29)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Embedding User Behavioral Aspect in TF-IDF Like Representation.\n \n \n \n \n\n\n \n Ligaj Pradhan; Chengcui Zhang; Steven Bethard; and Xin Chen.\n\n\n \n\n\n\n In 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pages 262-267, 4 2018. \n [Acceptance rate 20%]\n\n\n\n
\n\n\n\n \n \n \"EmbeddingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@INPROCEEDINGS{8397017,\nauthor={Ligaj Pradhan and Chengcui Zhang and Steven Bethard and Xin Chen},\nbooktitle={2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)},\ntitle={Embedding User Behavioral Aspect in TF-IDF Like Representation},\nyear={2018},\nvolume={},\nnumber={},\npages={262-267},\nkeywords={information retrieval, recommender systems},\nurl={http://doi.org/10.1109/MIPR.2018.00061},\nISSN={},\nmonth={4},\nnote = {[Acceptance rate 20\\%]},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Effects of Message Framing on Diabetes Screening Attitudes and Behavior.\n \n \n \n \n\n\n \n Stephen A. Rains; Melanie D. Hingle; Mihai Surdeanu; Dane Bell; and Stephen Kobourov.\n\n\n \n\n\n\n Manuscript in preparation. 2018.\n \n\n\n\n
\n\n\n\n \n \n \"EffectsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Rains:20182,\n        author = {Stephen A. Rains and Melanie D. Hingle and Mihai Surdeanu and Dane Bell and Stephen Kobourov},\n        title = {Effects of Message Framing on Diabetes Screening Attitudes and Behavior},\n        journal = {Manuscript in preparation},\n        year = {2018},\n        url = {http://clulab.org/papers/DiabetesMessageFramingStudyBriefReport.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Grounding Gradable Adjectives through Crowdsourcing.\n \n \n \n \n\n\n \n Rebecca Sharp; Mithun Paul; Ajay Nagesh; Dane Bell; and Mihai Surdeanu.\n\n\n \n\n\n\n In LREC 2018, 2018. \n \n\n\n\n
\n\n\n\n \n \n \"GroundingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 8 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{lrec2018,\n  title={Grounding Gradable Adjectives through Crowdsourcing},\n  author={Sharp, Rebecca and Paul, Mithun and Nagesh, Ajay and Bell, Dane and Surdeanu, Mihai},\n  booktitle={LREC 2018},\n  year={2018},\n  url={http://clulab.org/papers/GroundingGradableAdjectivesthroughCrowdsourcing.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Test of The Risk Perception Attitude Framework as a Message Tailoring Strategy to Promote Diabetes Screening.\n \n \n \n \n\n\n \n Stephen A. Rains; Melanie D. Hingle; Mihai Surdeanu; Dane Bell; and Stephen Kobourov.\n\n\n \n\n\n\n Health Communication. 2018.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n \n \"A odi\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@Article{Rains:2018,\n  author    = {Stephen A. Rains and Melanie D. Hingle and Mihai Surdeanu and Dane Bell and Stephen Kobourov},\n  title     = {A Test of The Risk Perception Attitude Framework as a Message Tailoring Strategy to Promote Diabetes Screening},\n  journal = {Health Communication},\n  url = {http://clulab.org/papers/RainsHingleSurdeanuetalHC.pdf},\n  url_odi = {https://doi.org/10.1080/10410236.2018.1431024},\n  year = {2018}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-hop Inference.\n \n \n \n \n\n\n \n Peter Jansen; Elizabeth Wainwright; Steven Marmorstein; and Clayton T. Morrison.\n\n\n \n\n\n\n In Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC), 2018. \n \n\n\n\n
\n\n\n\n \n \n \"WorldTree:Paper\n  \n \n \n \"WorldTree: code\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{jansen2018worldtree,\n    author = {Peter Jansen and Elizabeth Wainwright and Steven Marmorstein and Clayton T. Morrison},\n    title = {WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-hop Inference},\n    booktitle = {Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC)},\n    year = {2018},\n    url = {http://cognitiveai.org/wp-content/uploads/2018/02/jansen_et_al_lrec2018_worldtree_computable_explanation_corpus_8pg_cameraready.pdf},\n    url_code = {http://cognitiveai.org/explanationbank/}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Controlling Information Aggregation for Complex Question Answering.\n \n \n \n \n\n\n \n Heeyoung Kwon; Harsh Trivedi; Peter Jansen; Mihai Surdeanu; and Niranjan Balasubramanian.\n\n\n \n\n\n\n In Proceedings of the 40th European Conference on Information Retrieval (ECIR), 2018. \n \n\n\n\n
\n\n\n\n \n \n \"ControllingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{heeyoung2018ecir,\n    author = {Heeyoung Kwon and Harsh Trivedi and Peter Jansen and Mihai Surdeanu and Niranjan Balasubramanian},\n    title = {Controlling Information Aggregation for Complex Question Answering},\n    booktitle = {Proceedings of the 40th European Conference on Information Retrieval (ECIR)},\n    year = {2018},\n    url = {http://clulab.org/papers/ecir2018.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Text Annotation Graphs: Annotating Complex Natural Language Phenomena.\n \n \n \n \n\n\n \n Angus G. Forbes; Kristine Lee; Gus Hahn-Powell; Marco A. Valenzuela-Escarcega; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC'18), Miyazaki, Japan, May 2018. European Language Resources Association (ELRA)\n \n\n\n\n
\n\n\n\n \n \n \"Text code\n  \n \n \n \"TextPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{TAG-2018,\n    author = {Angus G. Forbes and Kristine Lee and Gus Hahn-Powell and Marco A. Valenzuela-Escarcega and Mihai Surdeanu},\n    title = {Text Annotation Graphs: Annotating Complex Natural Language Phenomena},\n    booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC'18)},\n    year = {2018},\n    month = {May},\n    address = {Miyazaki, Japan},\n    publisher = {European Language Resources Association (ELRA)},\n    url_code = {https://github.com/CreativeCodingLab/TextAnnotationGraphs},\n    url = {https://arxiv.org/pdf/1711.00529.pdf}\n }\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Keep your bearings: Lightly-supervised Information Extraction with Ladder Networks that avoids Semantic Drift.\n \n \n \n \n\n\n \n Ajay Nagesh; and Mihai Surdeanu.\n\n\n \n\n\n\n In NAACL HLT 2018, The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Louisiana, USA, Jun 1 - June 6, 2018, 2018. \n \n\n\n\n
\n\n\n\n \n \n \"KeepPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{DBLP:conf/naacl/ANMS18,\n  author    = {Ajay Nagesh and\n               Mihai Surdeanu},\n  title     = {Keep your bearings: Lightly-supervised Information Extraction with Ladder Networks that avoids Semantic Drift},\n  booktitle = {{NAACL} {HLT} 2018, The 16th Annual Conference of the North American Chapter\n               of the Association for Computational Linguistics: Human Language Technologies,\n               New Orleans, Louisiana, USA, Jun 1 - June 6, 2018},\n  year      = {2018},\n  url = {http://clulab.org/papers/naaclhlt2018.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Scientific Discovery as Link Prediction in Influence and Citation Graphs.\n \n \n \n \n\n\n \n Fan Luo; Marco A. Valenzuela-Escarcega; Gus Hahn-Powell; and Mihai Surdeanu.\n\n\n \n\n\n\n In TextGraphs: 12th Workshop on Graph-Based Natural Language Processing, 2018. NAACL\n \n\n\n\n
\n\n\n\n \n \n \"Scientific slides\n  \n \n \n \"ScientificPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 57 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{whitespaces-identification2018,\n  title={Scientific Discovery as Link Prediction in Influence and Citation Graphs},\n  author={Fan Luo and\n      \tMarco A. Valenzuela-Escarcega and\n        Gus Hahn-Powell and\n        Mihai Surdeanu},\n  booktitle = {TextGraphs: 12th Workshop on Graph-Based Natural Language Processing},\n  year={2018},\n  abstract = {We introduce a machine learning approach for the identification of ``white spaces'' in scientific knowledge. Our approach addresses this task as link prediction over a graph that contains over 2M influence statements such as ``CTCF activates FOXA1'', which were automatically extracted using open-domain machine reading. We model this prediction task using graph-based features extracted from the above influence graph, as well as from a citation graph that captures scientific communities. We evaluated the proposed approach through backtesting. Although the data is heavily unbalanced (50 times more negative examples than positives), our approach predicts which influence links will be discovered in the ``near future'' with a F1 score of 27 points, and a mean average precision of 68\\%. },\n  organization={NAACL},\n  url_Slides={http://clulab.org/papers/TextGraphs.pdf},\n  url={http://clulab.org/papers/ScientificDiscoveryasLinkPredictioninInfluenceandCitationGraphs.pdf}\n}\n
\n
\n\n\n
\n We introduce a machine learning approach for the identification of ``white spaces'' in scientific knowledge. Our approach addresses this task as link prediction over a graph that contains over 2M influence statements such as ``CTCF activates FOXA1'', which were automatically extracted using open-domain machine reading. We model this prediction task using graph-based features extracted from the above influence graph, as well as from a citation graph that captures scientific communities. We evaluated the proposed approach through backtesting. Although the data is heavily unbalanced (50 times more negative examples than positives), our approach predicts which influence links will be discovered in the ``near future'' with a F1 score of 27 points, and a mean average precision of 68%. \n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Sanity Check: A Strong Alignment and Information Retrieval Baseline for AI2 Reasoning Challenge.\n \n \n \n \n\n\n \n Vikas Yadav; Rebecca Sharp; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 2018. \n \n\n\n\n
\n\n\n\n \n \n \"SanityPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{vikasy_ARC_2018,\n  title={Sanity Check: A Strong Alignment and Information Retrieval Baseline for AI2 Reasoning Challenge},\n  author={Yadav, Vikas and Sharp, Rebecca and Surdeanu, Mihai},\n  booktitle = "Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)",\n  year={2018},\n  url = {https://arxiv.org/pdf/1807.01836.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Sanity Check: A Strong Alignment and Information Retrieval Baseline for AI2 Reasoning Challenge.\n \n \n \n \n\n\n \n Vikas Yadav; Rebecca Sharp; and Mihai Surdeanu.\n\n\n \n\n\n\n . 2018.\n \n\n\n\n
\n\n\n\n \n \n \"SanityPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{vikasy_ARC_2018,\n  title={Sanity Check: A Strong Alignment and Information Retrieval Baseline for AI2 Reasoning Challenge},\n  author={Yadav, Vikas and Sharp, Rebecca and Surdeanu, Mihai},\n  year={2018},\n  url = {https://arxiv.org/pdf/1807.01836.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Lightly-supervised Representation Learning with Global Interpretability.\n \n \n \n \n\n\n \n Marco A Valenzuela-Escarcega; Ajay Nagesh; and Mihai Surdeanu.\n\n\n \n\n\n\n In arXiv, 2018. \n \n\n\n\n
\n\n\n\n \n \n \"Lightly-supervisedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{lrec2018,\n  title={Lightly-supervised Representation Learning with Global Interpretability},\n  author={Valenzuela-Escarcega, Marco A  and Nagesh, Ajay and Surdeanu, Mihai},\n  booktitle={arXiv},\n  year={2018},\n  url={https://arxiv.org/abs/1805.11545/}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Grounding gradable adjectives through crowdsourcing.\n \n \n \n \n\n\n \n Rebecca Sharp; Mithun Paul; Ajay Nagesh; Dane Bell; and Mihai Surdeanu.\n\n\n \n\n\n\n In Nicoletta Calzolari; Khalid Choukri; Christopher Cieri; Thierry Declerck; Sara Goggi; Koiti Hasida; Hitoshi Isahara; Bente Maegaard; Joseph Mariani; Hélène Mazo; Asuncion Moreno; Jan Odijk; Stelios Piperidis; and Takenobu Tokunaga., editor(s), Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Paris, France, May 2018. European Language Resources Association (ELRA)\n \n\n\n\n
\n\n\n\n \n \n \"GroundingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 8 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{SHARP18.977,\n  author = {Rebecca Sharp and Mithun Paul and Ajay Nagesh and Dane Bell and Mihai Surdeanu},\n  title = {Grounding gradable adjectives through crowdsourcing},\n  booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},\n  year = {2018},\n  month = {May},\n  date = {7-12},\n  location = {Miyazaki, Japan},\n  editor = {Nicoletta Calzolari and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and H\\'{e}l\\`{e}ne Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga},\n  publisher = {European Language Resources Association (ELRA)},\n  address = {Paris, France},\n  isbn = {979-10-95546-00-9},\n  language = {english},\n  url = {http://www.lrec-conf.org/proceedings/lrec2018/pdf/977.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Detecting diabetes risk from social media activity.\n \n \n \n \n\n\n \n Dane Bell; Egoitz Laparra; Aditya Kousik; Terron Ishihara; Mihai Surdeanu; and Stephen Kobourov.\n\n\n \n\n\n\n In Ninth International Workshop on Health Text Mining and Information Analysis (LOUHI), 2018. \n \n\n\n\n
\n\n\n\n \n \n \"DetectingPaper\n  \n \n \n \"Detecting slides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 7 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{bell2018detecting,\n  title\t    = {Detecting diabetes risk from social media activity},\n  author    = {Bell, Dane and Laparra, Egoitz and Kousik, Aditya and Ishihara, Terron and Surdeanu, Mihai and Kobourov, Stephen},\n  booktitle = {Ninth International Workshop on Health Text Mining and Information Analysis (LOUHI)},\n  year      = {2018},\n  url = {http://clulab.org/papers/louhi2018-t2dmrisk.pdf},\n  url_Slides = {http://clulab.org/papers/louhi2018-emnlp.pptx}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Calorie estimation from pictures of food: Crowdsourcing study.\n \n \n \n \n\n\n \n Jun Zhou; Dane Bell; Sabina Nusrat; Melanie D.\\ Hingle; Mihai Surdeanu; and Stephen Kobourov.\n\n\n \n\n\n\n Interactive Journal of Medical Research (IJMR). 2018.\n \n\n\n\n
\n\n\n\n \n \n \"CaloriePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@Article{Zhou:2018,\n  author    = {Jun Zhou and Dane Bell and Sabina Nusrat and Melanie D.\\ Hingle and Mihai Surdeanu and Stephen Kobourov},\n  title     = {Calorie estimation from pictures of food: Crowdsourcing study},\n  journal = {Interactive Journal of Medical Research (IJMR)},\n  url = {http://clulab.org/papers/Zhou2018.pdf},\n  doi = {10.2196/ijmr.9359},\n  year = {2018}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n An Exploration of Three Lightly-supervised Representation Learning Approaches for Named Entity Classification.\n \n \n \n \n\n\n \n Ajay Nagesh; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 27th International Conference on Computational Linguistics, pages 2312-2324, 2018. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"AnPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{C18-1196,\n  author = \t"Nagesh, Ajay\n\t\tand Surdeanu, Mihai",\n  title = \t"An Exploration of Three Lightly-supervised Representation Learning Approaches for Named Entity Classification",\n  booktitle = \t"Proceedings of the 27th International Conference on Computational Linguistics",\n  year = \t"2018",\n  publisher = \t"Association for Computational Linguistics",\n  pages = \t"2312-2324",\n  location = \t"Santa Fe, New Mexico, USA",\n  url = \t"http://aclweb.org/anthology/C18-1196"\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Large-scale Automated Machine Reading Discovers New Cancer Driving Mechanisms.\n \n \n \n \n\n\n \n Marco A. Valenzuela-Escarcega; Ozgun Babur; Gus Hahn-Powell; Dane Bell; Thomas Hicks; Enrique Noriega-Atala; Xia Wang; Mihai Surdeanu; Emek Demir; and Clayton T. Morrison.\n\n\n \n\n\n\n Database: The Journal of Biological Databases and Curation. 2018.\n \n\n\n\n
\n\n\n\n \n \n \"Large-scalePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 34 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@Article{ValenzuelaEscarcega2018LargescaleAR,\n  title     = {Large-scale Automated Machine Reading Discovers New\nCancer Driving Mechanisms},\n  author  = {Valenzuela{-}Escarcega, Marco A. and Ozgun Babur and Gus Hahn-Powell and Dane Bell and Thomas Hicks and Enrique Noriega-Atala and Xia Wang and Mihai Surdeanu and Emek Demir and Clayton T. Morrison},\n  journal = {Database: The Journal of Biological Databases and Curation},\n  url = {http://clulab.org/papers/escarcega2018.pdf},\n  doi = {10.1093/database/bay098},\n  year = {2018}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Visual Supervision in Bootstrapped Information Extraction.\n \n \n \n \n\n\n \n Matthew Berger; Ajay Nagesh; Joshua A. Levine; Mihai Surdeanu; and Hao Helen Zhang.\n\n\n \n\n\n\n In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018. \n \n\n\n\n
\n\n\n\n \n \n \"VisualPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{berger2018emboot,\n  title={Visual Supervision in Bootstrapped Information Extraction},\n  author={Berger, Matthew and Nagesh, Ajay and Levine, Joshua A. and Surdeanu, Mihai and Zhang, Hao Helen},\n  booktitle={Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},\n  year={2018},\n  url={http://clulab.org/papers/emnlp2018.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Detecting Cyber Threats in Non-English Dark Net Markets: A Cross-Lingual Transfer Learning Approach.\n \n \n \n \n\n\n \n Mohammadreza Ebrahimi; Mihai Surdeanu; Sagar Samtani; and Hsinchun Chen.\n\n\n \n\n\n\n In Proceedings of the IEEE Intelligence and Security Informatics Conference (ISI), 2018. \n This paper won the Best Paper Runner-up Award.\n\n\n\n
\n\n\n\n \n \n \"DetectingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{Ebrahimi2018isi,\n    author = {Mohammadreza Ebrahimi and Mihai Surdeanu and Sagar Samtani and Hsinchun Chen},\n    title = {Detecting Cyber Threats in Non-English Dark Net Markets: A Cross-Lingual Transfer Learning Approach},\n    booktitle = {Proceedings of the IEEE Intelligence and Security Informatics Conference (ISI)},\n    year = {2018},\n    note = {This paper won the Best Paper Runner-up Award.},\n    url = {http://clulab.org/papers/isi2018.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Machine Reading for Scientific Discovery.\n \n \n \n \n\n\n \n Gus Hahn-Powell.\n\n\n \n\n\n\n Ph.D. Thesis, 2018.\n \n\n\n\n
\n\n\n\n \n \n \"MachinePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@phdthesis{ghpdiss2018,\n        author = {Gus Hahn-Powell},\n        publisher = {The University of Arizona},\n        year = {2018},\n        title = {Machine Reading for Scientific Discovery},\n        url = {https://repository.arizona.edu/handle/10150/630562}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction.\n \n \n \n \n\n\n \n Chen Lin; Timothy Miller; Dmitriy Dligach; Hadi Amiri; Steven Bethard; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis, pages 165–176, Brussels, Belgium, 10 2018. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Self-trainingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{lin-EtAl:2018:LOUHI,\n  author    = {Lin, Chen  and  Miller, Timothy  and  Dligach, Dmitriy  and  Amiri, Hadi  and  Bethard, Steven  and  Savova, Guergana},\n  title     = {Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction},\n  booktitle = {Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis},\n  month     = {10},\n  year      = {2018},\n  address   = {Brussels, Belgium},\n  publisher = {Association for Computational Linguistics},\n  pages     = {165--176},\n  url       = {http://www.aclweb.org/anthology/W18-5619},\n  keywords = {timelines, information extraction, health applications, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Survey on Recent Advances in Named Entity Recognition from Deep Learning models.\n \n \n \n \n\n\n \n Vikas Yadav; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 27th International Conference on Computational Linguistics, pages 2145–2158, Santa Fe, New Mexico, USA, 8 2018. Association for Computational Linguistics\n [Acceptance rate 37%]\n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{yadav-bethard:2018:C18-1,\n  author    = {Yadav, Vikas  and  Bethard, Steven},\n  title     = {A Survey on Recent Advances in Named Entity Recognition from Deep Learning models},\n  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},\n  month     = {8},\n  year      = {2018},\n  address   = {Santa Fe, New Mexico, USA},\n  publisher = {Association for Computational Linguistics},\n  pages     = {2145--2158},\n  url       = {http://www.aclweb.org/anthology/C18-1182},\n  note = {[Acceptance rate 37\\%]},\n  keywords = {information extraction},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of The 12th International Workshop on Semantic Evaluation (SemEval-2018).\n \n \n \n \n\n\n \n Marianna Apidianaki; Saif M. Mohammad; Jonathan May; Ekaterina Shutova; Steven Bethard; and Marine Carpuat.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. New Orleans, Louisiana, 6 2018.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@proceedings{apidianaki-etal:2018:SemEval,\n  editor    = {Marianna Apidianaki  and  Saif M. Mohammad  and  Jonathan May  and  Ekaterina Shutova  and  Steven Bethard  and  Marine Carpuat},\n  title     = {Proceedings of The 12th International Workshop on Semantic Evaluation (SemEval-2018)},\n  month     = {6},\n  year      = {2018},\n  address   = {New Orleans, Louisiana},\n  publisher = {Association for Computational Linguistics},\n  url       = {http://www.aclweb.org/anthology/S18-1},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n SemEval 2018 Task 6: Parsing Time Normalizations.\n \n \n \n \n\n\n \n Egoitz Laparra; Dongfang Xu; Ahmed Elsayed; Steven Bethard; and Martha Palmer.\n\n\n \n\n\n\n In Proceedings of The 12th International Workshop on Semantic Evaluation, pages 88–96, New Orleans, Louisiana, 6 2018. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"SemEvalPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{laparra-etal:2018:SemEval,\n  author    = {Laparra, Egoitz  and  Xu, Dongfang  and  Elsayed, Ahmed  and  Bethard, Steven  and  Palmer, Martha},\n  title     = {SemEval 2018 Task 6: Parsing Time Normalizations},\n  booktitle = {Proceedings of The 12th International Workshop on Semantic Evaluation},\n  month     = {6},\n  year      = {2018},\n  address   = {New Orleans, Louisiana},\n  publisher = {Association for Computational Linguistics},\n  pages     = {88--96},\n  url       = {http://www.aclweb.org/anthology/S18-1011},\n  keywords  = {timelines, information extraction, shared task paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Deep Affix Features Improve Neural Named Entity Recognizers.\n \n \n \n \n\n\n \n Vikas Yadav; Rebecca Sharp; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, pages 167–172, New Orleans, Louisiana, 6 2018. Association for Computational Linguistics\n [Acceptance rate 29%]\n\n\n\n
\n\n\n\n \n \n \"DeepPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{yadav-sharp-bethard:2018:SEM,\n  author    = {Yadav, Vikas  and  Sharp, Rebecca  and  Bethard, Steven},\n  title     = {Deep Affix Features Improve Neural Named Entity Recognizers},\n  booktitle = {Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics},\n  month     = {6},\n  year      = {2018},\n  address   = {New Orleans, Louisiana},\n  publisher = {Association for Computational Linguistics},\n  pages     = {167--172},\n  url       = {http://www.aclweb.org/anthology/S18-2021},\n  note = {[Acceptance rate 29\\%]},\n  keywords  = {information extraction},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations.\n \n \n \n \n\n\n \n Egoitz Laparra; Dongfang Xu; and Steven Bethard.\n\n\n \n\n\n\n Transactions of the Association for Computational Linguistics, 6: 343–356. 5 2018.\n \n\n\n\n
\n\n\n\n \n \n \"FromPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@article{laparra-xu-bethard:2018:TACL,\n        author = {Laparra, Egoitz  and Xu, Dongfang  and Bethard, Steven },\n        title = {From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations},\n        journal = {Transactions of the Association for Computational Linguistics},\n        volume = {6},\n        year = {2018},\n        month = {5},\n        day = {31},\n        keywords = {timelines, information extraction},\n        issn = {2307-387X},\n        url = {https://transacl.org/ojs/index.php/tacl/article/view/1318},\n        pages = {343--356}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n UArizona at the MADE1.0 NLP Challenge.\n \n \n \n \n\n\n \n Dongfang Xu; Vikas Yadav; and Steven Bethard.\n\n\n \n\n\n\n In Feifan Liu; Abhyuday Jagannatha; and Hong Yu., editor(s), Proceedings of the 1st International Workshop on Medication and Adverse Drug Event Detection, volume 90, of Proceedings of Machine Learning Research, pages 57–65, 5 2018. \n \n\n\n\n
\n\n\n\n \n \n \"UArizonaPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{xu-yadav-bethard:2018:MADE,\n  title = \t {UArizona at the MADE1.0 NLP Challenge},\n  author = \t {Dongfang Xu and Vikas Yadav and Steven Bethard},\n  booktitle = \t {Proceedings of the 1st International Workshop on Medication and Adverse Drug Event Detection},\n  pages = \t {57--65},\n  year = \t {2018},\n  editor = \t {Feifan Liu and Abhyuday Jagannatha and Hong Yu},\n  volume = \t {90},\n  series = \t {Proceedings of Machine Learning Research},\n  address = \t {},\n  month = \t {5},\n  url = \t {http://proceedings.mlr.press/v90/xu18a.html},\n  keywords = {semantic relations, information extraction, health applications, shared task paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Measuring the Latency of Depression Detection in Social Media.\n \n \n \n \n\n\n \n Farig Sadeque; Dongfang Xu; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, of WSDM '18, pages 495–503, New York, NY, USA, 2 2018. ACM\n [Acceptance rate 16%]\n\n\n\n
\n\n\n\n \n \n \"MeasuringPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@inproceedings{sadeque-xu-bethard:2018:WSDM,\n author = {Sadeque, Farig and Xu, Dongfang and Bethard, Steven},\n title = {Measuring the Latency of Depression Detection in Social Media},\n booktitle = {Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining},\n series = {WSDM '18},\n year = {2018},\n month = {2},\n isbn = {978-1-4503-5581-0},\n location = {Marina Del Rey, CA, USA},\n pages = {495--503},\n numpages = {9},\n url = {http://doi.acm.org/10.1145/3159652.3159725},\n doi = {10.1145/3159652.3159725},\n acmid = {3159725},\n publisher = {ACM},\n address = {New York, NY, USA},\n  note = {[Acceptance rate 16\\%]},\n keywords = {health applications, social media},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n CUILESS2016: a clinical corpus applying compositional normalization of text mentions.\n \n \n \n \n\n\n \n John D. Osborne; Matthew B. Neu; Maria I. Danila; Thamar Solorio; and Steven J. Bethard.\n\n\n \n\n\n\n Journal of Biomedical Semantics, 9(1): 2. 1 2018.\n \n\n\n\n
\n\n\n\n \n \n \"CUILESS2016:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@Article{osborne-etal:2018:JBS,\nauthor="Osborne, John D.\nand Neu, Matthew B.\nand Danila, Maria I.\nand Solorio, Thamar\nand Bethard, Steven J.",\ntitle="CUILESS2016: a clinical corpus applying compositional normalization of text mentions",\njournal="Journal of Biomedical Semantics",\nyear="2018",\nmonth="1",\nday="10",\nvolume="9",\nnumber="1",\npages="2",\nissn="2041-1480",\ndoi="10.1186/s13326-017-0173-6",\nurl="https://doi.org/10.1186/s13326-017-0173-6",\nkeywords = {annotation, term normalization, health applications},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2017\n \n \n (18)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification.\n \n \n \n \n\n\n \n Rebecca Sharp; Mihai Surdeanu; Peter Jansen; Marco A Valenzuela-Escarcega; Peter Clark; and Michael Hammond.\n\n\n \n\n\n\n In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 69-79, 2017. \n \n\n\n\n
\n\n\n\n \n \n \"TellPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{sharp2017tell,\n  title={Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification},\n  author={Sharp, Rebecca and Surdeanu, Mihai and Jansen, Peter and Valenzuela-Escarcega, Marco A and Clark, Peter and Hammond, Michael},\n  booktitle={Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)},\n  pages={69-79},\n  year={2017},\n  url={http://www.aclweb.org/anthology/K17-1009}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Framing QA as Building and Ranking Intersentence Answer Justifications.\n \n \n \n \n\n\n \n Peter Jansen; Rebecca Sharp; Mihai Surdeanu; and Peter Clark.\n\n\n \n\n\n\n Computational Linguistics. 2017.\n \n\n\n\n
\n\n\n\n \n \n \"FramingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{jansen2017framing,\n  title={Framing QA as Building and Ranking Intersentence Answer Justifications},\n  author={Jansen, Peter and Sharp, Rebecca and Surdeanu, Mihai and Clark, Peter},\n  journal={Computational Linguistics},\n  year={2017},\n  publisher={MIT Press},\n  url={http://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00287}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Learning what to read: Focused machine reading.\n \n \n \n \n\n\n \n Enrique Noriega-Atala; Marco A Valenzuela-Escarcega; Clayton Morrison; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2895-2900, 2017. \n \n\n\n\n
\n\n\n\n \n \n \"LearningPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{noriega2017learning,\n  title={Learning what to read: Focused machine reading},\n  author={Noriega-Atala, Enrique and Valenzuela-Escarcega, Marco A and Morrison, Clayton and Surdeanu, Mihai},\n  booktitle={Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},\n  pages={2895-2900},\n  year={2017},\n  url={https://arxiv.org/pdf/1709.00149.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A scaffolding approach to coreference resolution integrating statistical and rule-based models.\n \n \n \n \n\n\n \n Heeyoung Lee; Mihai Surdeanu; and Dan Jurafsky.\n\n\n \n\n\n\n Natural Language Engineering,1-30. 2017.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{lee2017scaffolding,\n  title={A scaffolding approach to coreference resolution integrating statistical and rule-based models},\n  author={Lee, Heeyoung and Surdeanu, Mihai and Jurafsky, Dan},\n  journal={Natural Language Engineering},\n  pages={1-30},\n  year={2017},\n  publisher={Cambridge University Press},\n  url={https://www.cambridge.org/core/services/aop-cambridge-core/content/view/042D0D6C6E125EFB939E0F2C2E63152B/S1351324917000109a.pdf/div-class-title-a-scaffolding-approach-to-coreference-resolution-integrating-statistical-and-rule-based-models-div.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Swanson linking revisited: Accelerating literature-based discovery across domains using a conceptual influence graph.\n \n \n \n \n\n\n \n Gus Hahn-Powell; Marco A Valenzuela-Escarcega; and Mihai Surdeanu.\n\n\n \n\n\n\n Proceedings of ACL 2017, System Demonstrations,103-108. 2017.\n \n\n\n\n
\n\n\n\n \n \n \"SwansonPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{hahn2017swanson,\n  title={Swanson linking revisited: Accelerating literature-based discovery across domains using a conceptual influence graph},\n  author={Hahn-Powell, Gus and Valenzuela-Escarcega, Marco A and Surdeanu, Mihai},\n  journal={Proceedings of ACL 2017, System Demonstrations},\n  pages={103-108},\n  year={2017},\n  url={http://www.aclweb.org/anthology/P17-4018}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Focused Reading: Reinforcement Learning for What Documents to Read.\n \n \n \n \n\n\n \n Enrique Noriega-Atala; Marco A. Valenzuela-Escarcega; Clayton T. Morrison; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Interactive Machine Learning and Semantic Information Retrieval Workshop at ICML, 2017, 2017. \n \n\n\n\n
\n\n\n\n \n \n \"FocusedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{enrique2017focused,\n  title={Focused Reading: Reinforcement Learning for What Documents to Read},\n  author={Enrique Noriega-Atala and Marco A. Valenzuela-Escarcega and Clayton T. Morrison and Mihai Surdeanu},\n  booktitle={Proceedings of the Interactive Machine Learning and Semantic Information Retrieval Workshop at ICML, 2017},\n  year={2017},\n  url={http://clulab.org/papers/focusedreading2017.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Large-scale automated reading with Reach discovers new cancer driving mechanisms.\n \n \n \n \n\n\n \n Marco A. Valenzuela-Escarcega; Ozgun Babur; Gus Hahn-Powell; Dane Bell; Thomas Hicks; Enrique Noriega-Atala; Xia Wang; Mihai Surdeanu; Emek Demir; and Clayton T. Morrison.\n\n\n \n\n\n\n In Proceedings of the Sixth BioCreative Challenge Evaluation Workshop, pages 201-203, 2017. \n \n\n\n\n
\n\n\n\n \n \n \"Large-scalePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{biocreative6,\ntitle={{Large-scale automated reading with Reach discovers new cancer driving mechanisms}},\nauthor={Valenzuela-Escarcega, Marco A. and Ozgun Babur and Gus Hahn-Powell and Dane Bell and Thomas Hicks and Enrique Noriega-Atala and Xia Wang and Mihai Surdeanu and Emek Demir and Clayton T. Morrison},\npages={201-203},\nyear={2017},\nbooktitle={Proceedings of the Sixth BioCreative Challenge Evaluation Workshop},\nurl={http://clulab.org/papers/biocreative6.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Study of Automatically Acquiring Explanatory Inference Patterns from Corpora of Explanations: Lessons from Elementary Science Exams.\n \n \n \n \n\n\n \n Peter Jansen.\n\n\n \n\n\n\n In Proceedings of the 2017 Workshop on Automated Knowledge Base Construction, of AKBC'17, 2017. \n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n \n \"A data\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{jansen:akbc2017,\n author = {Peter Jansen},\n title = {A Study of Automatically Acquiring Explanatory Inference Patterns from Corpora of Explanations: Lessons from Elementary Science Exams},\n booktitle = {Proceedings of the 2017 Workshop on Automated Knowledge Base Construction},\n series = {AKBC'17},\n year = {2017},\n url = {http://cognitiveai.org/wp-content/uploads/2017/11/jansen_akbc2017_automatically_acquiring_explanatory_inference_patterns_from_corpora_of_explanations.pdf},\n url_data = {http://cognitiveai.org/explanationbank/}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments.\n \n \n \n \n\n\n \n Quynh Ngoc Thi Do; Steven Bethard; and Marie-Francine Moens.\n\n\n \n\n\n\n In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 90–99, Taipei, Taiwan, 11 2017. Asian Federation of Natural Language Processing\n [Acceptance rate 31%]\n\n\n\n
\n\n\n\n \n \n \"ImprovingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{do-bethard-moens:2017:I17-1,\n  author    = {Do, Quynh Ngoc Thi  and  Bethard, Steven  and  Moens, Marie-Francine},\n  title     = {Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments},\n  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},\n  month     = {11},\n  year      = {2017},\n  address   = {Taipei, Taiwan},\n  publisher = {Asian Federation of Natural Language Processing},\n  pages     = {90--99},\n  url       = {http://www.aclweb.org/anthology/I17-1010},\n  note = {[Acceptance rate 31\\%]},\n  keywords = {semantic relations},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n UArizona at the CLEF eRisk 2017 Pilot Task: Linear and Recurrent Models for Early Depression Detection.\n \n \n \n \n\n\n \n Farig Sadeque; Dongfang Xu; and Steven Bethard.\n\n\n \n\n\n\n In CEUR workshop proceedings: Working Notes of CLEF 2017 - Conference and Labs of the Evaluation Forum, Dublin, Ireland, 9 2017. \n \n\n\n\n
\n\n\n\n \n \n \"UArizonaPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{sadeque-xu-bethard:2017:CLEF,\n  author = {Farig Sadeque and Dongfang Xu and Steven Bethard},\n  title = {{UArizona} at the {CLEF eRisk} 2017 Pilot Task: Linear and Recurrent Models for Early Depression Detection},\n  booktitle = {CEUR workshop proceedings: Working Notes of CLEF 2017 - Conference and Labs of the Evaluation Forum},\n  address = {Dublin, Ireland},\n  month = {9},\n  year = {2017},\n  url = {http://ceur-ws.org/Vol-1866/paper_58.pdf},\n  keywords = {health applications, social media, shared task paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Infusing Latent User-Concerns from User Reviews into Collaborative Filtering.\n \n \n \n \n\n\n \n Ligaj Pradhan; Chengcui Zhang; and Steven Bethard.\n\n\n \n\n\n\n In 2017 IEEE International Conference on Information Reuse and Integration (IRI), pages 471-477, 8 2017. \n [Acceptance rate 29%]\n\n\n\n
\n\n\n\n \n \n \"InfusingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@INPROCEEDINGS{pradhan-zhang-bethard:2017:IRI,\nauthor = {Ligaj Pradhan and Chengcui Zhang and Steven Bethard},\nbooktitle = {2017 IEEE International Conference on Information Reuse and Integration (IRI)},\ntitle = {Infusing Latent User-Concerns from User Reviews into Collaborative Filtering},\nyear = {2017},\nvolume = {},\nnumber = {},\npages = {471-477},\ndoi = {10.1109/IRI.2017.24},\nurl = {http://doi.ieeecomputersociety.org/10.1109/IRI.2017.24},\nmonth={8},\nnote = {[Acceptance rate 29\\%]},\nkeywords = {information retrieval, recommender systems},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks.\n \n \n \n \n\n\n \n Chen Lin; Timothy Miller; Dmitriy Dligach; Steven Bethard; and Guergana Savova.\n\n\n \n\n\n\n In BioNLP 2017, pages 322–327, Vancouver, Canada,, 8 2017. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"RepresentationsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{lin-EtAl:2017:BioNLP17,\n  author    = {Lin, Chen  and  Miller, Timothy  and  Dligach, Dmitriy  and  Bethard, Steven  and  Savova, Guergana},\n  title     = {Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks},\n  booktitle = {BioNLP 2017},\n  month     = {8},\n  year      = {2017},\n  address   = {Vancouver, Canada,},\n  publisher = {Association for Computational Linguistics},\n  pages     = {322--327},\n  url       = {http://www.aclweb.org/anthology/W17-2341},\n  keywords = {timelines, information extraction, health applications, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Unsupervised Domain Adaptation for Clinical Negation Detection.\n \n \n \n \n\n\n \n Timothy Miller; Steven Bethard; Hadi Amiri; and Guergana Savova.\n\n\n \n\n\n\n In BioNLP 2017, pages 165–170, Vancouver, Canada,, 8 2017. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"UnsupervisedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{miller-EtAl:2017:BioNLP17,\n  author    = {Miller, Timothy  and  Bethard, Steven  and  Amiri, Hadi  and  Savova, Guergana},\n  title     = {Unsupervised Domain Adaptation for Clinical Negation Detection},\n  booktitle = {BioNLP 2017},\n  month     = {8},\n  year      = {2017},\n  address   = {Vancouver, Canada,},\n  publisher = {Association for Computational Linguistics},\n  pages     = {165--170},\n  url       = {http://www.aclweb.org/anthology/W17-2320},\n  keywords = {negation, domain adaptation, health applications, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n SemEval-2017 Task 12: Clinical TempEval.\n \n \n \n \n\n\n \n Steven Bethard; Guergana Savova; Martha Palmer; and James Pustejovsky.\n\n\n \n\n\n\n In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 565–572, Vancouver, Canada, 8 2017. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"SemEval-2017Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{bethard-EtAl:2017:SemEval,\n  author    = {Bethard, Steven  and  Savova, Guergana  and  Palmer, Martha  and  Pustejovsky, James},\n  title     = {SemEval-2017 Task 12: Clinical TempEval},\n  booktitle = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)},\n  month     = {8},\n  year      = {2017},\n  address   = {Vancouver, Canada},\n  publisher = {Association for Computational Linguistics},\n  pages     = {565--572},\n  url       = {http://www.aclweb.org/anthology/S17-2093},\n  keywords = {timelines, information extraction, health applications, domain adaptation, shared task paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017).\n \n \n \n \n\n\n \n Steven Bethard; Marine Carpuat; Marianna Apidianaki; Saif M. Mohammad; Daniel Cer; and David Jurgens.,\n editors.\n \n\n\n \n\n\n\n Association for Computational Linguistics. Vancouver, Canada, 8 2017.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@proceedings{SemEval:2017,\n  editor    = {Steven Bethard  and  Marine Carpuat  and  Marianna Apidianaki  and  Saif M. Mohammad  and  Daniel Cer  and  David Jurgens},\n  title     = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)},\n  month     = {8},\n  year      = {2017},\n  address   = {Vancouver, Canada},\n  publisher = {Association for Computational Linguistics},\n  url       = {http://www.aclweb.org/anthology/S17-2},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Recurrent Neural Network Architectures for Event Extraction from Italian Medical Reports.\n \n \n \n \n\n\n \n Natalia Viani; Timothy A. Miller; Dmitriy Dligach; Steven Bethard; Carlo Napolitano; Silvia G. Priori; Riccardo Bellazzi; Lucia Sacchi; and Guergana K. Savova.\n\n\n \n\n\n\n In Annette Teije; Christian Popow; John H. Holmes; and Lucia Sacchi., editor(s), Artificial Intelligence in Medicine: 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings, pages 198–202, Cham, 2017. Springer International Publishing\n [Acceptance rate 39%]\n\n\n\n
\n\n\n\n \n \n \"RecurrentPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{viani-EtAl:2017:AIME,\nauthor="Viani, Natalia\nand Miller, Timothy A.\nand Dligach, Dmitriy\nand Bethard, Steven\nand Napolitano, Carlo\nand Priori, Silvia G.\nand Bellazzi, Riccardo\nand Sacchi, Lucia\nand Savova, Guergana K.",\neditor="ten Teije, Annette\nand Popow, Christian\nand Holmes, John H.\nand Sacchi, Lucia",\ntitle="Recurrent Neural Network Architectures for Event Extraction from Italian Medical Reports",\nbookTitle="Artificial Intelligence in Medicine: 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings",\nyear="2017",\npublisher="Springer International Publishing",\naddress="Cham",\npages="198--202",\nisbn="978-3-319-59758-4",\ndoi="10.1007/978-3-319-59758-4_21",\nurl="https://doi.org/10.1007/978-3-319-59758-4_21",\nnote = {[Acceptance rate 39\\%]},\nkeywords = {timelines, information extraction, health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Towards generalizable entity-centric clinical coreference resolution .\n \n \n \n \n\n\n \n Timothy Miller; Dmitriy Dligach; Steven Bethard; Chen Lin; and Guergana Savova.\n\n\n \n\n\n\n Journal of Biomedical Informatics , 69: 251 - 258. 2017.\n \n\n\n\n
\n\n\n\n \n \n \"TowardsPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@article{miller-EtAl:2017:JBI,\ntitle = "Towards generalizable entity-centric clinical coreference resolution ",\njournal = "Journal of Biomedical Informatics ",\nvolume = "69",\nnumber = "",\npages = "251 - 258",\nyear = "2017",\nnote = "",\nissn = "1532-0464",\ndoi = "https://doi.org/10.1016/j.jbi.2017.04.015",\nurl = "http://www.sciencedirect.com/science/article/pii/S1532046417300850",\nauthor = "Timothy Miller and Dmitriy Dligach and Steven Bethard and Chen Lin and Guergana Savova",\nkeywords = {coreference, health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Neural Temporal Relation Extraction.\n \n \n \n \n\n\n \n Dmitriy Dligach; Timothy Miller; Chen Lin; Steven Bethard; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 746–751, Valencia, Spain, 4 2017. Association for Computational Linguistics\n [Acceptance rate 24%]\n\n\n\n
\n\n\n\n \n \n \"NeuralPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{dligach-EtAl:2017:EACLshort,\n  author    = {Dligach, Dmitriy  and  Miller, Timothy  and  Lin, Chen  and  Bethard, Steven  and  Savova, Guergana},\n  title     = {Neural Temporal Relation Extraction},\n  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},\n  month     = {4},\n  year      = {2017},\n  address   = {Valencia, Spain},\n  publisher = {Association for Computational Linguistics},\n  pages     = {746--751},\n  url       = {http://www.aclweb.org/anthology/E17-2118},\n  note = {[Acceptance rate 24\\%]},\n  keywords = {timelines, information extraction, health applications},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2016\n \n \n (15)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n What's in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams.\n \n \n \n \n\n\n \n Peter Jansen; Niranjan Balasubramanian; Mihai Surdeanu; and Peter Clark.\n\n\n \n\n\n\n In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2956-2965, Osaka, Japan, December 2016. The COLING 2016 Organizing Committee\n \n\n\n\n
\n\n\n\n \n \n \"What'sPaper\n  \n \n \n \"What's data\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{jansen-EtAl:2016:COLING,\n  author    = {Jansen, Peter  and  Balasubramanian, Niranjan  and  Surdeanu, Mihai  and  Clark, Peter},\n  title     = {What's in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams},\n  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},\n  month     = {December},\n  year      = {2016},\n  address   = {Osaka, Japan},\n  publisher = {The COLING 2016 Organizing Committee},\n  pages     = {2956-2965},\n  url       = {http://aclweb.org/anthology/C16-1278},\n  url_Data  = {http://allenai.org/data.html},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction.\n \n \n \n \n\n\n \n Marco A. Valenzuela-Escarcega; Gustave Hahn-Powell; Dane Bell; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2016 Workshop on Biomedical Natural Language Processing (BioNLP 2016), 2016. \n \n\n\n\n
\n\n\n\n \n \n \"SnapToGrid:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{Valenzuela:16b,\n  author    = {Valenzuela-Escarcega, Marco A. and Gustave Hahn-Powell and Dane Bell and Mihai Surdeanu},\n  title     = {SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction},\n  booktitle = {Proceedings of the 2016 Workshop on Biomedical Natural Language Processing (BioNLP 2016)},\n  year      = {2016},\n  url       = {https://arxiv.org/abs/1606.09604},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n This before That: Causal Precedence in the Biomedical Domain.\n \n \n \n \n\n\n \n Gustave Hahn-Powell; Dane Bell; Marco A. Valenzuela-Escarcega; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 2016 Workshop on Biomedical Natural Language Processing (BioNLP 2016), 2016. \n Latest results can be found at https://repository.arizona.edu/handle/10150/630562\n\n\n\n
\n\n\n\n \n \n \"ThisPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{HahnPowell:16,\n  author    = {Gustave Hahn-Powell and Dane Bell and Valenzuela-Escarcega, Marco A. and Mihai Surdeanu},\n  title     = {This before That: Causal Precedence in the Biomedical Domain},\n  booktitle = {Proceedings of the 2016 Workshop on Biomedical Natural Language Processing (BioNLP 2016)},\n  year      = {2016},\n  url       = {https://arxiv.org/abs/1606.08089},\n  note         = {Latest results can be found at {https://repository.arizona.edu/handle/10150/630562}}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Creating Causal Embeddings for Question Answering with Minimal Supervision.\n \n \n \n \n\n\n \n Rebecca Sharp; Mihai Surdeanu; Peter Jansen; Peter Clark; and Michael Hammond.\n\n\n \n\n\n\n In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2016. \n \n\n\n\n
\n\n\n\n \n \n \"CreatingPaper\n  \n \n \n \"Creating data and code\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 8 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Sharp2016,\n\tyear = {2016},\n\tauthor = {Sharp, Rebecca and Mihai Surdeanu and Peter Jansen and Peter Clark and Michael Hammond},\n\tbooktitle = {Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},\n\ttitle = {Creating Causal Embeddings for Question Answering with Minimal Supervision},\n  url = {http://arxiv.org/abs/1609.08097},\n  url_Data_and_Code = {http://clulab.org/data/emnlp2016-causal/},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n An Investigation of Coreference Phenomena in the Biomedical Domain.\n \n \n \n \n\n\n \n Dane Bell; Gustave Hahn-Powell; Marco A. Valenzuela-Escarcega; Gustave Hahn-Powell; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC), 2016. \n \n\n\n\n
\n\n\n\n \n \n \"AnPaper\n  \n \n \n \"An code\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{Bell:16,\n  author    = {Bell, Dane and Gustave Hahn-Powell and Marco A. Valenzuela-Escarcega and Gustave Hahn-Powell  and Mihai Surdeanu},\n  title     = {An Investigation of Coreference Phenomena in the Biomedical Domain},\n  booktitle = {Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC)},\n  year      = {2016},\n  url       = {http://clulab.org/papers/lrec2016-coref.pdf},\n  url_Code  = {https://github.com/clulab/reach},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Odin's Runes: A Rule Language for Information Extraction.\n \n \n \n \n\n\n \n Marco A. Valenzuela-Escarcega; Gustave Hahn-Powell; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC), 2016. \n \n\n\n\n
\n\n\n\n \n \n \"Odin'sPaper\n  \n \n \n \"Odin's code\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 14 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{Valenzuela:16,\n  author    = {Valenzuela-Escarcega, Marco A. and Gustave Hahn-Powell  and Mihai Surdeanu},\n  title     = {Odin's Runes: A Rule Language for Information Extraction},\n  booktitle = {Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC)},\n  year      = {2016},\n  url       = {http://surdeanu.info/mihai/papers/lrec2016-odin.pdf},\n  url_Code  = {https://github.com/sistanlp/processors},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Towards Using Social Media to Identify Individuals at Risk for Preventable Chronic Illness.\n \n \n \n \n\n\n \n Dane Bell; Daniel Fried; Luwen Huangfu; Mihai Surdeanu; and Stephen Kobourov.\n\n\n \n\n\n\n In Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC), 2016. \n \n\n\n\n
\n\n\n\n \n \n \"TowardsPaper\n  \n \n \n \"Towards code\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{Bell:16b,\n  author    = {Bell, Dane and Daniel Fried and Luwen Huangfu and Mihai Surdeanu and Stephen Kobourov},\n  title     = {Towards Using Social Media to Identify Individuals at Risk for Preventable Chronic Illness},\n  booktitle = {Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC)},\n  year      = {2016},\n  url       = {http://clulab.org/papers/lrec2016-t4f.pdf},\n  url_Code  = {https://github.com/clulab/twitter4food},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Extracting Hierarchy of Coherent User-Concerns to Discover Intricate User Behavior from User Reviews.\n \n \n \n \n\n\n \n Ligaj Pradhan; Chengcui Zhang; and Steven Bethard.\n\n\n \n\n\n\n International Journal of Multimedia Data Engineering and Management (IJMDEM), 7(4): 63–80. 2016.\n \n\n\n\n
\n\n\n\n \n \n \"ExtractingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@article{pradhan2016extracting,\n  title={Extracting Hierarchy of Coherent User-Concerns to Discover Intricate User Behavior from User Reviews},\n  author={Pradhan, Ligaj and Zhang, Chengcui and Bethard, Steven},\n  journal={International Journal of Multimedia Data Engineering and Management (IJMDEM)},\n  volume={7},\n  number={4},\n  pages={63--80},\n  year={2016},\n  publisher={IGI Global},\n  url={https://dx.doi.org/10.4018/IJMDEM.2016100104},\n  keywords={information retrieval, recommender systems},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP).\n \n \n \n \n\n\n \n Anna Rumshisky; Kirk Roberts; Steven Bethard; and Tristan Naumann.,\n editors.\n \n\n\n \n\n\n\n The COLING 2016 Organizing Committee. Osaka, Japan, 12 2016.\n \n\n\n\n
\n\n\n\n \n \n \"ProceedingsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@proceedings{ClinicalNLP:2016,\n  editor    = {Anna Rumshisky  and  Kirk Roberts  and  Steven Bethard  and  Tristan Naumann},\n  title     = {Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP)},\n  month     = {12},\n  year      = {2016},\n  address   = {Osaka, Japan},\n  publisher = {The COLING 2016 Organizing Committee},\n  url       = {http://aclweb.org/anthology/W16-42},\n  keywords = {health applications},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training.\n \n \n \n \n\n\n \n Quynh Ngoc Thi Do; Steven Bethard; and Marie-Francine Moens.\n\n\n \n\n\n\n In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1275–1284, Osaka, Japan, 12 2016. The COLING 2016 Organizing Committee\n [Acceptance rate 32%]\n\n\n\n
\n\n\n\n \n \n \"FacingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{do-bethard-moens:2016:COLING,\n  author    = {Do, Quynh Ngoc Thi  and  Bethard, Steven  and  Moens, Marie-Francine},\n  title     = {Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training},\n  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},\n  month     = {12},\n  year      = {2016},\n  address   = {Osaka, Japan},\n  publisher = {The COLING 2016 Organizing Committee},\n  pages     = {1275--1284},\n  url       = {http://aclweb.org/anthology/C16-1121},\n  note = {[Acceptance rate 32\\%]},\n  keywords = {semantic relations, domain adaptation},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Why Do They Leave: Modeling Participation in Online Depression Forums.\n \n \n \n \n\n\n \n Farig Sadeque; Ted Pedersen; Thamar Solorio; Prasha Shrestha; Nicolas Rey-Villamizar; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of The Fourth International Workshop on Natural Language Processing for Social Media, pages 14–19, Austin, TX, USA, 11 2016. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"WhyPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{sadeque-EtAl:2016:SocialNLP,\n  author    = {Sadeque, Farig  and  Pedersen, Ted  and  Solorio, Thamar  and  Shrestha, Prasha  and  Rey-Villamizar, Nicolas  and  Bethard, Steven},\n  title     = {Why Do They Leave: Modeling Participation in Online Depression Forums},\n  booktitle = {Proceedings of The Fourth International Workshop on Natural Language Processing for Social Media},\n  month     = {11},\n  year      = {2016},\n  address   = {Austin, TX, USA},\n  publisher = {Association for Computational Linguistics},\n  pages     = {14--19},\n  url       = {http://aclweb.org/anthology/W16-6203},\n  keywords = {health applications, social media, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Analysis of Anxious Word Usage on Online Health Forums.\n \n \n \n \n\n\n \n Nicolas Rey-Villamizar; Prasha Shrestha; Farig Sadeque; Steven Bethard; Ted Pedersen; Arjun Mukherjee; and Thamar Solorio.\n\n\n \n\n\n\n In Proceedings of the Seventh International Workshop on Health Text Mining and Information Analysis, pages 37–42, Auxtin, TX, 11 2016. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"AnalysisPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{reyvillamizar-EtAl:2016:LOUHI,\n  author    = {Rey-Villamizar, Nicolas  and  Shrestha, Prasha  and  Sadeque, Farig  and  Bethard, Steven  and  Pedersen, Ted  and  Mukherjee, Arjun  and  Solorio, Thamar},\n  title     = {Analysis of Anxious Word Usage on Online Health Forums},\n  booktitle = {Proceedings of the Seventh International Workshop on Health Text Mining and Information Analysis},\n  month     = {11},\n  year      = {2016},\n  address   = {Auxtin, TX},\n  publisher = {Association for Computational Linguistics},\n  pages     = {37--42},\n  url       = {http://aclweb.org/anthology/W16-6105},\n  keywords = {health applications, social media, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Visualizing the Content of a Children's Story in a Virtual World: Lessons Learned.\n \n \n \n \n\n\n \n Quynh Ngoc Thi Do; Steven Bethard; and Marie-Francine Moens.\n\n\n \n\n\n\n In Proceedings of the Workshop on Uphill Battles in Language Processing: Scaling Early Achievements to Robust Methods, pages 39–42, Austin, TX, 11 2016. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"VisualizingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{do-bethard-moens:2016:UBLP,\n  author    = {Do, Quynh Ngoc Thi  and  Bethard, Steven  and  Moens, Marie-Francine},\n  title     = {Visualizing the Content of a Children's Story in a Virtual World: Lessons Learned},\n  booktitle = {Proceedings of the Workshop on Uphill Battles in Language Processing: Scaling Early Achievements to Robust Methods},\n  month     = {11},\n  year      = {2016},\n  address   = {Austin, TX},\n  publisher = {Association for Computational Linguistics},\n  pages     = {39--42},\n  url       = {http://aclweb.org/anthology/W16-6009},\n  keywords = {coreference, semantic relations, educational applications, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Improving Temporal Relation Extraction with Training Instance Augmentation.\n \n \n \n \n\n\n \n Chen Lin; Timothy Miller; Dmitriy Dligach; Steven Bethard; and Guergana Savova.\n\n\n \n\n\n\n In Proceedings of the 15th Workshop on Biomedical Natural Language Processing, pages 108–113, Berlin, Germany, 8 2016. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ImprovingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{lin-EtAl:2016:BioNLP16,\n  author    = {Lin, Chen  and  Miller, Timothy  and  Dligach, Dmitriy  and  Bethard, Steven  and  Savova, Guergana},\n  title     = {Improving Temporal Relation Extraction with Training Instance Augmentation},\n  booktitle = {Proceedings of the 15th Workshop on Biomedical Natural Language Processing},\n  month     = {8},\n  year      = {2016},\n  address   = {Berlin, Germany},\n  publisher = {Association for Computational Linguistics},\n  pages     = {108--113},\n  url       = {http://anthology.aclweb.org/W16-2914},\n  keywords = {timelines, information extraction, health applications, workshop paper},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Domain Adaptation for Authorship Attribution: Improved Structural Correspondence Learning.\n \n \n \n \n\n\n \n Upendra Sapkota; Thamar Solorio; Manuel Montes; and Steven Bethard.\n\n\n \n\n\n\n In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2226–2235, Berlin, Germany, 8 2016. Association for Computational Linguistics\n [Acceptance rate 28%]\n\n\n\n
\n\n\n\n \n \n \"DomainPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@InProceedings{sapkota-EtAl:2016:P16-1,\n  author    = {Sapkota, Upendra  and  Solorio, Thamar  and  Montes, Manuel  and  Bethard, Steven},\n  title     = {Domain Adaptation for Authorship Attribution: Improved Structural Correspondence Learning},\n  booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},\n  month     = {8},\n  year      = {2016},\n  address   = {Berlin, Germany},\n  publisher = {Association for Computational Linguistics},\n  pages     = {2226--2235},\n  url       = {http://www.aclweb.org/anthology/P16-1210},\n  note = {[Acceptance rate 28\\%]},\n  keywords = {authorship analysis, domain adaptation},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2015\n \n \n (7)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Identifying meaningful citations.\n \n \n \n \n\n\n \n Marco Valenzuela; Vu Ha; and Oren Etzioni.\n\n\n \n\n\n\n In Proceedings of the \"Scholarly Big Data: AI Perspectives, Challenges, and Ideas\" Workshop at the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015. \n \n\n\n\n
\n\n\n\n \n \n \"IdentifyingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{valenzuela2015identifying,\n  title={Identifying meaningful citations},\n  author={Valenzuela, Marco and Ha, Vu and Etzioni, Oren},\n  booktitle={Proceedings of the "Scholarly Big Data: AI Perspectives, Challenges, and Ideas" Workshop at the Twenty-Ninth AAAI Conference on Artificial Intelligence},\n  year={2015},\n  url={http://ai2-website.s3.amazonaws.com/publications/ValenzuelaHaMeaningfulCitations.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Domain-independent Rule-based Framework for Event Extraction.\n \n \n \n \n\n\n \n Marco A. Valenzuela-Escarcega; Gustave Hahn-Powell; Thomas Hicks; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Assian Federation of Natural Language Processing: Software Demonstrations (ACL-IJCNLP), 2015. \n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n \n \"A code\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{Valenzuela:15,\n  author    = {Valenzuela-Escarcega, Marco A. and Gustave Hahn-Powell and Thomas Hicks and Mihai Surdeanu},\n  title     = {A Domain-independent Rule-based Framework for Event Extraction},\n  booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Assian Federation of Natural Language Processing: Software Demonstrations (ACL-IJCNLP)},\n  year      = {2015},\n  url      = {http://clulab.org/papers/acl2015.pdf},\n  url_Code  = {https://github.com/sistanlp/processors},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Two Practical Rhetorical Structure Theory Parsers.\n \n \n \n \n\n\n \n Mihai Surdeanu; Thomas Hicks; and Marco A. Valenzuela-Escarcega.\n\n\n \n\n\n\n In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT): Software Demonstrations, 2015. \n \n\n\n\n
\n\n\n\n \n \n \"TwoPaper\n  \n \n \n \"Two code\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{Surdeanu:15,\n  author    = {Surdeanu, Mihai and Thomas Hicks and Marco A. Valenzuela-Escarcega},\n  title     = {Two Practical Rhetorical Structure Theory Parsers},\n  booktitle = {Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT): Software Demonstrations},\n  year      = {2015},\n  url       = {http://clulab.org/papers/naacl2015-discourse.pdf},\n  url_Code  = {https://github.com/sistanlp/processors},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Diamonds in the Rough: Event Extraction from Imperfect Microblog Data.\n \n \n \n \n\n\n \n Ander Intxaurrondo; Eneko Agirre; Oier Lopez Lacalle; and Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), 2015. \n \n\n\n\n
\n\n\n\n \n \n \"DiamondsPaper\n  \n \n \n \"Diamonds data\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{Intxaurrondo:15,\n  author    = {Intxaurrondo, Ander and Eneko Agirre and Oier Lopez de Lacalle and Mihai Surdeanu},\n  title     = {Diamonds in the Rough: Event Extraction from Imperfect Microblog Data},\n  booktitle = {Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT)},\n  year      = {2015},\n  url       = {http://clulab.org/papers/naacl2015-ee.pdf},\n  url_Data  = {http://ixa.eus/Ixa/Argitalpenak/Artikuluak/1425465524/publikoak/earthquake-kb-dataset.zip},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering.\n \n \n \n \n\n\n \n Rebecca Sharp; Peter Jansen; Mihai Surdeanu; and Peter Clark.\n\n\n \n\n\n\n In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), 2015. \n \n\n\n\n
\n\n\n\n \n \n \"SpinningPaper\n  \n \n \n \"Spinning data and some code\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{Sharp:15,\n  author    = {Sharp, Rebecca and Peter Jansen and Mihai Surdeanu and Peter Clark},\n  title     = {Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering},\n  booktitle = {Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT)},\n  year      = {2015},\n  url       = {http://clulab.org/papers/naacl2015-qa.pdf},\n  url_Data_and_Some_Code = {http://surdeanu.cs.arizona.edu/mihai/papers/straw2gold.zip},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Higher-order Lexical Semantic Models for Non-factoid Answer Reranking.\n \n \n \n \n\n\n \n Daniel Fried; Peter Jansen; Gustave Hahn-Powell; Mihai Surdeanu; and Peter Clark.\n\n\n \n\n\n\n Transactions of the Association for Computational Linguistics, 3: 197-210. 2015.\n \n\n\n\n
\n\n\n\n \n \n \"Higher-orderPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Fried:2015,\n        author = {Daniel Fried and Peter Jansen and Gustave Hahn-Powell and Mihai\nSurdeanu and Peter Clark},\n        title = {Higher-order Lexical Semantic Models for Non-factoid Answer\nReranking},\n        journal = {Transactions of the Association for Computational Linguistics},\n        volume = {3},\n        year = {2015},\n        keywords = {},\n        abstract = {Lexical semantic models provide robust performance for question\nanswering, but, in general, can only capitalize on direct evidence seen\nduring training. For example, monolingual alignment models acquire term\nalignment probabilities from semi-structured data such as question-answer\npairs; neural network language models learn term embeddings from\nunstructured text. All this knowledge is then used to estimate the semantic\nsimilarity between question and answer candidates.  We introduce a\nhigher-order formalism that allows all these lexical semantic models to\nchain direct evidence to construct indirect associations between question\nand answer texts, by casting the task as the traversal of graphs that encode\ndirect term associations.  Using a corpus of 10,000 questions from Yahoo!\nAnswers, we experimentally demonstrate that higher-order methods are broadly\napplicable to alignment and language models, across both word and syntactic\nrepresentations. We show that an important criterion for success is\ncontrolling for the semantic drift that accumulates during graph traversal.\nAll in all, the proposed higher-order approach improves five out of the six\nlexical semantic models investigated, with relative gains of up to +13\\%\nover their first-order variants. },\n        issn = {2307-387X},\n        url =\n{https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/550},\n        pages = {197-210}\n}\n
\n
\n\n\n
\n Lexical semantic models provide robust performance for question answering, but, in general, can only capitalize on direct evidence seen during training. For example, monolingual alignment models acquire term alignment probabilities from semi-structured data such as question-answer pairs; neural network language models learn term embeddings from unstructured text. All this knowledge is then used to estimate the semantic similarity between question and answer candidates. We introduce a higher-order formalism that allows all these lexical semantic models to chain direct evidence to construct indirect associations between question and answer texts, by casting the task as the traversal of graphs that encode direct term associations. Using a corpus of 10,000 questions from Yahoo! Answers, we experimentally demonstrate that higher-order methods are broadly applicable to alignment and language models, across both word and syntactic representations. We show that an important criterion for success is controlling for the semantic drift that accumulates during graph traversal. All in all, the proposed higher-order approach improves five out of the six lexical semantic models investigated, with relative gains of up to +13% over their first-order variants. \n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Description of the odin event extraction framework and rule language.\n \n \n \n \n\n\n \n Marco A Valenzuela-Escarcega; Gus Hahn-Powell; and Mihai Surdeanu.\n\n\n \n\n\n\n arXiv preprint arXiv:1509.07513. 2015.\n \n\n\n\n
\n\n\n\n \n \n \"DescriptionPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 25 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{valenzuela2015description,\n  title={Description of the odin event extraction framework and rule language},\n  author={Valenzuela-Escarcega, Marco A and Hahn-Powell, Gus and Surdeanu, Mihai},\n  journal={arXiv preprint arXiv:1509.07513},\n  year={2015},\n  url={https://arxiv.org/pdf/1509.07513},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2014\n \n \n (7)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Discourse Complements Lexical Semantics for Non-factoid Answer Reranking.\n \n \n \n \n\n\n \n Peter Jansen; Mihai Surdeanu; and Peter Clark.\n\n\n \n\n\n\n In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), 2014. \n \n\n\n\n
\n\n\n\n \n \n \"DiscoursePaper\n  \n \n \n \"Discourse code and data\n  \n \n \n \"Discourse slides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Jansen:14,\n\tyear = {2014},\n\tauthor = {Jansen, Peter and Surdeanu, Mihai and Clark, Peter},\n\tbooktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)},\n\ttitle = {Discourse Complements Lexical Semantics for Non-factoid Answer Reranking},\n  url = {http://clulab.org/papers/acl2014.pdf},\n  url_Code_And_Data = {http://nlp.sista.arizona.edu/releases/acl2014/},\n  url_Slides = {http://nlp.sista.arizona.edu/releases/acl2014/},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n The Stanford CoreNLP Natural Language Processing Toolkit.\n \n \n \n \n\n\n \n Christopher D. Manning; Mihai Surdeanu; John Bauer; Jenny Finkel; Steven J. Bethard; and David McClosky.\n\n\n \n\n\n\n In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), 2014. \n \n\n\n\n
\n\n\n\n \n \n \"ThePaper\n  \n \n \n \"The code\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Manning:14,\n\tyear = {2014},\n\tauthor = {Manning, Christopher D. and Surdeanu, Mihai and Bauer, John and Finkel, Jenny and Bethard, Steven J. and McClosky, David},\n\tbooktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)},\n\ttitle = {The Stanford CoreNLP Natural Language Processing Toolkit},\n  url = {http://clulab.org/papers/acl2014-corenlp.pdf},\n  url_Code = {http://nlp.stanford.edu/software/corenlp.shtml},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Analyzing the Language of Food on Social Media.\n \n \n \n \n\n\n \n Daniel Fried; Mihai Surdeanu; Stephen Kobourov; Melanie Hingle; and Dane Bell.\n\n\n \n\n\n\n In Proceedings of the 2014 IEEE International Conference on Big Data, 2014. \n \n\n\n\n
\n\n\n\n \n \n \"AnalyzingPaper\n  \n \n \n \"Analyzing supplmental material\n  \n \n \n \"Analyzing demo\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Fried:14,\n\tyear = {2014},\n\tauthor = {Fried, Daniel and Surdeanu, Mihai and Kobourov, Stephen and Hingle, Melanie and Bell, Dane},\n\tbooktitle = {Proceedings of the 2014 IEEE International Conference on Big Data},\n\ttitle = {Analyzing the Language of Food on Social Media},\n  url = {http://clulab.org/papers/bigdata2014.pdf},\n  url_Supplmental_Material = {http://arxiv.org/abs/1409.2195},\n  url_Demo = {https://sites.google.com/site/twitter4food/},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Overview of the English Slot Filling Track at the TAC2014 Knowledge Base Population Evaluation.\n \n \n \n \n\n\n \n Mihai Surdeanu; and Ji Heng.\n\n\n \n\n\n\n In Proceedings of the TAC-KBP 2014 Workshop, 2014. \n \n\n\n\n
\n\n\n\n \n \n \"OverviewPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{SurdeanuHeng:14,\n\tyear = {2014},\n\tauthor = {Surdeanu, Mihai and Heng, Ji},\n\tbooktitle = {Proceedings of the TAC-KBP 2014 Workshop},\n\ttitle = {Overview of the English Slot Filling Track at the TAC2014 Knowledge Base Population Evaluation},\n  url = {http://clulab.org/papers/kbp2014_draft.pdf},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Event Extraction Using Distant Supervision.\n \n \n \n \n\n\n \n Kevin Reschke; Martin Jankowiak; Mihai Surdeanu; Christopher D. Manning; and Dan Jurafsky.\n\n\n \n\n\n\n In Proceedings of the 9th edition of the Language Resources and Evaluation Conference (LREC), 2014. \n \n\n\n\n
\n\n\n\n \n \n \"EventPaper\n  \n \n \n \"Event data\n  \n \n \n \"Event slides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Reschke:14,\n\tyear = {2014},\n\tauthor = {Reschke, Kevin and Jankowiak, Martin and Surdeanu, Mihai and Manning, Christopher D. and Jurafsky, Dan},\n\tbooktitle = {Proceedings of the 9th edition of the Language Resources and Evaluation Conference (LREC)},\n\ttitle = {Event Extraction Using Distant Supervision},\n  url = {http://clulab.org/papers/lrec2014_ds.pdf},\n  url_Data = {http://nlp.stanford.edu/projects/dist-sup-event-extraction.shtml},\n  url_Slides = {http://clulab.org/papers/lrec2014_ds_slides.pdf}\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n On the Importance of Text Analysis for Stock Price Prediction.\n \n \n \n \n\n\n \n Heeyoung Lee; Bill MacCartney; Mihai Surdeanu; and Dan Jurafsky.\n\n\n \n\n\n\n In Proceedings of the 9th edition of the Language Resources and Evaluation Conference (LREC), 2014. \n \n\n\n\n
\n\n\n\n \n \n \"OnPaper\n  \n \n \n \"On data\n  \n \n \n \"On slides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Lee:14,\n\tyear = {2014},\n\tauthor = {Lee, Heeyoung and MacCartney, Bill and Surdeanu, Mihai and Jurafsky, Dan},\n\tbooktitle = {Proceedings of the 9th edition of the Language Resources and Evaluation Conference (LREC)},\n\ttitle = {On the Importance of Text Analysis for Stock Price Prediction},\n  url = {http://clulab.org/papers/lrec2014_stocks.pdf},\n  url_Data = {http://nlp.stanford.edu/pubs/stock-event.html},\n  url_Slides = {http://clulab.org/papers/lrec2014_stocks_slides.pdf},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Extracting Latent Attributes from Video Scenes Using Text as Background Knowledge.\n \n \n \n \n\n\n \n Anh Tran; Mihai Surdeanu; and Paul Cohen.\n\n\n \n\n\n\n In Proceedings of the Third Joint Conference on Lexical and Computational Semantics (*SEM), 2014. \n \n\n\n\n
\n\n\n\n \n \n \"ExtractingPaper\n  \n \n \n \"Extracting slides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Tran:14,\n\tyear = {2014},\n\tauthor = {Tran, Anh and Surdeanu, Mihai and Cohen, Paul},\n\tbooktitle = {Proceedings of the Third Joint Conference on Lexical and Computational Semantics (*SEM)},\n\ttitle = {Extracting Latent Attributes from Video Scenes Using Text as Background Knowledge},\n  url = {http://clulab.org/papers/starsem2014.pdf},\n  url_Slides = {http://clulab.org/papers/starsem2014_slides.pdf},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2013\n \n \n (7)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Selectional Preferences for Semantic Role Classification.\n \n \n \n \n\n\n \n Benat Zapirain; Eneko Agirre; Lluis Marquez; and Mihai Surdeanu.\n\n\n \n\n\n\n Computational Linguistics, 39(3). 2013.\n \n\n\n\n
\n\n\n\n \n \n \"SelectionalPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@Article{Zapirain:13,\n  author    = {Benat Zapirain and Eneko Agirre and Lluis Marquez and Mihai Surdeanu},\n  title     = {Selectional Preferences for Semantic Role Classification},\n  journal = {Computational Linguistics},\n  volume = {39},\n  number = {3},\n  year      = {2013},\n  url = {http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00145},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Deterministic coreference resolution based on entity-centric, precision-ranked rules.\n \n \n \n \n\n\n \n Heeyoung Lee; Angel Chang; Yves Peirsman; Nathanael Chambers; Mihai Surdeanu; and Dan Jurafsky.\n\n\n \n\n\n\n Computational Linguistics, 39(4). 2013.\n \n\n\n\n
\n\n\n\n \n \n \"DeterministicPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@Article{Lee:13,\n  author    = {Heeyoung Lee and Angel Chang and Yves Peirsman and Nathanael Chambers and Mihai Surdeanu and Dan Jurafsky},\n  title     = {Deterministic coreference resolution based on entity-centric, precision-ranked rules},\n  journal = {Computational Linguistics},\n  volume = {39},\n  number = {4},\n  year      = {2013},\n  url = {http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00152},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Identifying Patent Monetization Entities.\n \n \n \n \n\n\n \n Mihai Surdeanu; and Sara Jeruss.\n\n\n \n\n\n\n In Proceedings of the XIV International Conference on Artificial Intelligence and Law (ICAIL), 2013. \n \n\n\n\n
\n\n\n\n \n \n \"IdentifyingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{surdeanu2013-icail,\n\tyear = {2013},\n\tauthor = {Mihai Surdeanu and Sara Jeruss},\n\tbooktitle = {Proceedings of the XIV International Conference on Artificial Intelligence and Law (ICAIL)},\n\ttitle = {Identifying Patent Monetization Entities},\n  url = {http://clulab.org/papers/icail2013.pdf},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Overview of the TAC2013 Knowledge Base Population Evaluation: English Slot Filling and Temporal Slot Filling.\n \n \n \n \n\n\n \n Mihai Surdeanu.\n\n\n \n\n\n\n In Proceedings of the TAC-KBP 2013 Workshop, 2013. \n \n\n\n\n
\n\n\n\n \n \n \"OverviewPaper\n  \n \n \n \"Overview slides sf\n  \n \n \n \"Overview slides tsf\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Surdeanu:13,\n\tyear = {2013},\n\tauthor = {Surdeanu, Mihai},\n\tbooktitle = {Proceedings of the TAC-KBP 2013 Workshop},\n\ttitle = {Overview of the TAC2013 Knowledge Base Population Evaluation: English Slot Filling and Temporal Slot Filling},\n  url = {http://clulab.org/papers/kbp2013.pdf},\n  url_Slides_SF = {http://clulab.org/papers/kbp2013_sf.pdf},\n  url_Slides_TSF = {http://clulab.org/papers/kbp2013_tsf.pdf},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Removing Noisy Mentions for Distant Supervision.\n \n \n \n \n\n\n \n Ander Intxaurrondo; Mihai Surdeanu; Oier Lopez Lacalle; and Eneko Agirre.\n\n\n \n\n\n\n In Proceedings of the 29th \"Congreso de la Sociedad Española para el Procesamiento del Lenguaje Natural\" (SEPLN 2013), 2013. \n \n\n\n\n
\n\n\n\n \n \n \"RemovingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{intxaurrondo13,\n\tyear = {2013},\n\tauthor = {Ander Intxaurrondo and Mihai Surdeanu and Oier Lopez de Lacalle and Eneko Agirre},\n\tbooktitle = {Proceedings of the 29th "Congreso de la Sociedad Espa{\\~{n}}ola para el Procesamiento del Lenguaje Natural" (SEPLN 2013)},\n\ttitle = {Removing Noisy Mentions for Distant Supervision},\n  url = {http://clulab.org/papers/sepln13.pdf},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Transmitting Narrative: An Interactive Shift-Summarization Tool for Improving Nurse Communication.\n \n \n \n \n\n\n \n Angus Forbes; Mihai Surdeanu; Peter Jansen; and Jane Carrington.\n\n\n \n\n\n\n In Proceedings of the 3rd IEEE Workshop on Interactive Visual Text Analytics, 2013. \n \n\n\n\n
\n\n\n\n \n \n \"TransmittingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Forbes:13,\n\tyear = {2013},\n\tauthor = {Angus Forbes and Mihai Surdeanu and Peter Jansen and Jane Carrington},\n\tbooktitle = {Proceedings of the 3rd IEEE Workshop on Interactive Visual Text Analytics},\n\ttitle = {Transmitting Narrative: An Interactive Shift-Summarization Tool for Improving Nurse Communication},\n  url = {http://clulab.org/papers/textvis2013.pdf},\n}\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Bayesian modeling of scenes and captions.\n \n \n \n \n\n\n \n Luca Del Pero Colin R. Dawson Clayton T. Morrison , Mihai Surdeanu Gustave Hahn-Powell Zachary Chapman; and Kobus Barnard.\n\n\n \n\n\n\n In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2013), Workshop on Vision and Language (WVL), 2013. \n \n\n\n\n
\n\n\n\n \n \n \"Bayesian slides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{Colin:NAACLHLT2013,\ntitle={Bayesian modeling of scenes and captions},\nauthor={Colin R. Dawson, Luca Del Pero, Clayton T. Morrison, Mihai Surdeanu, Gustave Hahn-Powell, Zachary Chapman and Kobus Barnard},\nyear={2013},\nbooktitle={Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2013), Workshop on Vision and Language (WVL)},\nurl_Slides={http://surdeanu.info/mihai/papers/wvl2013_slides.pdf},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n undefined\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Extracting Crop Model Parameters from Literature Using Natural Language Processing.\n \n \n \n \n\n\n \n Maria Alexeeva; Vijaya R Joshi; Hubert Kanyamahanga; Isaac Kobby Anni; Keith Alcock; Gerrit Hoogenboom; and Mihai Surdeanu.\n\n\n \n\n\n\n Presented at AI in Agriculture: Innovation and Discovery to Equitably Meet Producer Needs and Perceptions Conference, Orlando, Florida, .\n \n\n\n\n
\n\n\n\n \n \n \"Extracting poster\n  \n \n \n \"Extracting abstract\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 6 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
\n
\n\n\n\n
\n\n\n\n\n\n    
\n  
\n\n\n\n\n  
\n\n\n  \n\n  \n  \n  \n  \n\n
\n"}; document.write(bibbase_data.data);