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%2Fapi.zotero.org%2Fusers%2F5414994%2Fcollections%2F86KRVVHK%2Fitems%3Fkey%3DR4LGq2FsV4FTfuDPOljwMZOi%26format%3Dbibtex%26limit%3D100&jsonp=1&jsonp=1\"></script>\n \n
\n\n PHP\n
\n \n <?php\n $contents = file_get_contents(\"https://bibbase.org/show?bib=https%3A%2F%2Fapi.zotero.org%2Fusers%2F5414994%2Fcollections%2F86KRVVHK%2Fitems%3Fkey%3DR4LGq2FsV4FTfuDPOljwMZOi%26format%3Dbibtex%26limit%3D100&jsonp=1\");\n print_r($contents);\n ?>\n \n
\n\n iFrame\n (not recommended)\n
\n \n <iframe src=\"https://bibbase.org/show?bib=https%3A%2F%2Fapi.zotero.org%2Fusers%2F5414994%2Fcollections%2F86KRVVHK%2Fitems%3Fkey%3DR4LGq2FsV4FTfuDPOljwMZOi%26format%3Dbibtex%26limit%3D100&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 2023\n \n \n (4)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Answer-state Recurrent Relational Network (AsRRN) for Constructed Response Assessment and Feedback Grouping.\n \n \n \n \n\n\n \n Li, Z.; Lloyd, S.; Beckman, M.; and Passonneau, R.\n\n\n \n\n\n\n In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3879–3891, Singapore, 2023. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"Answer-statePaper\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 
@inproceedings{li_answer-state_2023,\n\taddress = {Singapore},\n\ttitle = {Answer-state {Recurrent} {Relational} {Network} ({AsRRN}) for {Constructed} {Response} {Assessment} and {Feedback} {Grouping}},\n\turl = {https://aclanthology.org/2023.findings-emnlp.254},\n\tdoi = {10.18653/v1/2023.findings-emnlp.254},\n\tlanguage = {en},\n\turldate = {2024-01-12},\n\tbooktitle = {Findings of the {Association} for {Computational} {Linguistics}: {EMNLP} 2023},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Li, Zhaohui and Lloyd, Susan and Beckman, Matthew and Passonneau, Rebecca},\n\tyear = {2023},\n\tpages = {3879--3891},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Learning When to Defer to Humans for Short Answer Grading.\n \n \n \n \n\n\n \n Li, Z.; Zhang, C.; Jin, Y.; Cang, X.; Puntambekar, S.; and Passonneau, R. J.\n\n\n \n\n\n\n In Wang, N.; Rebolledo-Mendez, G.; Matsuda, N.; Santos, O. C.; and Dimitrova, V., editor(s), Artificial Intelligence in Education, volume 13916, pages 414–425. Springer Nature Switzerland, Cham, 2023.\n Series Title: Lecture Notes in Computer Science\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 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@incollection{wang_learning_2023,\n\taddress = {Cham},\n\ttitle = {Learning {When} to {Defer} to {Humans} for {Short} {Answer} {Grading}},\n\tvolume = {13916},\n\tisbn = {978-3-031-36271-2 978-3-031-36272-9},\n\turl = {https://link.springer.com/10.1007/978-3-031-36272-9_34},\n\tlanguage = {en},\n\turldate = {2023-07-17},\n\tbooktitle = {Artificial {Intelligence} in {Education}},\n\tpublisher = {Springer Nature Switzerland},\n\tauthor = {Li, Zhaohui and Zhang, Chengning and Jin, Yumi and Cang, Xuesong and Puntambekar, Sadhana and Passonneau, Rebecca J.},\n\teditor = {Wang, Ning and Rebolledo-Mendez, Genaro and Matsuda, Noboru and Santos, Olga C. and Dimitrova, Vania},\n\tyear = {2023},\n\tdoi = {10.1007/978-3-031-36272-9_34},\n\tnote = {Series Title: Lecture Notes in Computer Science},\n\tpages = {414--425},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n AI for Coding Education Meta-Analyses: An Open-Science Approach that Combines Human and Machine Intelligence.\n \n \n \n\n\n \n Gupta, V.; Belland, B. R.; Billups, A.; and Passonneau, R. J.\n\n\n \n\n\n\n In 4th International Conference on Artificial Intelligence in Education Technology, volume Lecture Notes on Data Engineering and Communications Technology, to appear., Berlin, Germany, 2023. Springer\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{gupta_ai_2023,\n\taddress = {Berlin, Germany},\n\ttitle = {{AI} for {Coding} {Education} {Meta}-{Analyses}: {An} {Open}-{Science} {Approach} that {Combines} {Human} and {Machine} {Intelligence}},\n\tvolume = {Lecture Notes on Data Engineering and Communications Technology, to appear.},\n\tabstract = {Meta-analysis provides researchers with a way to assess the efficacy of an educational intervention across multiple independent studies by integrating them into a single statistical analysis, and thereby generalize over a larger, more heterogeneous population. This influences the ability to address goals of diversity, equity and inclusion (DEI), by providing a perspective over different populations of students. However, meta-analysis is extremely costly, mainly due to the need to manually code each of the many articles selected for inclusion, for each relevant variable. To shorten the time to publication, lower the cost, enhance transparency, and enable periodic updates of a given meta-analysis, we propose an open-science approach to meta-analysis coding that provides distinct modules for each variable, and that combines human and automated effort. We illustrate the approach on two variables that represent two types of automated support: pattern matching, versus machine learning. On the latter, we leverage a human-in-the loop approach for a variable that identifies distinct student populations, and is thus important for DEI: we report high accuracy of a neural model, and even higher accuracy of a selective prediction approach that defers to humans when the model output is insufficiently confident.},\n\tbooktitle = {4th {International} {Conference} on {Artificial} {Intelligence} in {Education} {Technology}},\n\tpublisher = {Springer},\n\tauthor = {Gupta, Vipul and Belland, Brian R. and Billups, Alexander and Passonneau, Rebecca J.},\n\tyear = {2023},\n}\n\n
\n
\n\n\n
\n Meta-analysis provides researchers with a way to assess the efficacy of an educational intervention across multiple independent studies by integrating them into a single statistical analysis, and thereby generalize over a larger, more heterogeneous population. This influences the ability to address goals of diversity, equity and inclusion (DEI), by providing a perspective over different populations of students. However, meta-analysis is extremely costly, mainly due to the need to manually code each of the many articles selected for inclusion, for each relevant variable. To shorten the time to publication, lower the cost, enhance transparency, and enable periodic updates of a given meta-analysis, we propose an open-science approach to meta-analysis coding that provides distinct modules for each variable, and that combines human and automated effort. We illustrate the approach on two variables that represent two types of automated support: pattern matching, versus machine learning. On the latter, we leverage a human-in-the loop approach for a variable that identifies distinct student populations, and is thus important for DEI: we report high accuracy of a neural model, and even higher accuracy of a selective prediction approach that defers to humans when the model output is insufficiently confident.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n The Ideal versus the Real Deal in Assessment of Physics Lab Report Writing.\n \n \n \n\n\n \n Passonneau, R. J.; Koenig, K.; Li, Z.; and Soddano, J.\n\n\n \n\n\n\n European Journal of Applied Sciences, 11(2): 626–644. 2023.\n \n\n\n\n
\n\n\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 \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{passonneau_ideal_2023,\n\ttitle = {The {Ideal} versus the {Real} {Deal} in {Assessment} of {Physics} {Lab} {Report} {Writing}},\n\tvolume = {11},\n\tdoi = {https://doi.org/10.14738/aivp.112.14406},\n\tabstract = {Effective writing is important for communicating science ideas, and for writing-to-learn in science. This paper investigates lab reports from a large-enrollment college physics course that integrates scientific reasoning and science writing. While analytic rubrics have been shown to define expectations more clearly for students, and to improve reliability of assessment, there has been little investigation of how well analytic rubrics serve students and instructors in large-enrollment science classes. Unsurprisingly, we found that grades administered by teaching assistants (TAs) do not correlate with reliable post-hoc assessments from trained raters. More important, we identified lost learning opportunities for students, and misinformation for instructors about students’ progress. We believe our methodology to achieve post-hoc reliability is straightforward enough to be used in classrooms. A key element is the development of finer-grained rubrics for grading that are aligned with the rubrics provided to students to define expectations, but which reduce subjectivity of judgements and grading time. We conclude that the use of dual rubrics, one to elicit independent reasoning from students and one to clarify grading criteria, could improve reliability and accountability of lab report assessment, which could in turn elevate the role of lab reports in the instruction of scientific inquiry.},\n\tnumber = {2},\n\tjournal = {European Journal of Applied Sciences},\n\tauthor = {Passonneau, Rebecca J. and Koenig, Kathleen and Li, Zhaohui and Soddano, Josephine},\n\tyear = {2023},\n\tpages = {626--644},\n}\n\n
\n
\n\n\n
\n Effective writing is important for communicating science ideas, and for writing-to-learn in science. This paper investigates lab reports from a large-enrollment college physics course that integrates scientific reasoning and science writing. While analytic rubrics have been shown to define expectations more clearly for students, and to improve reliability of assessment, there has been little investigation of how well analytic rubrics serve students and instructors in large-enrollment science classes. Unsurprisingly, we found that grades administered by teaching assistants (TAs) do not correlate with reliable post-hoc assessments from trained raters. More important, we identified lost learning opportunities for students, and misinformation for instructors about students’ progress. We believe our methodology to achieve post-hoc reliability is straightforward enough to be used in classrooms. A key element is the development of finer-grained rubrics for grading that are aligned with the rubrics provided to students to define expectations, but which reduce subjectivity of judgements and grading time. We conclude that the use of dual rubrics, one to elicit independent reasoning from students and one to clarify grading criteria, could improve reliability and accountability of lab report assessment, which could in turn elevate the role of lab reports in the instruction of scientific inquiry.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2022\n \n \n (6)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication.\n \n \n \n \n\n\n \n Zare, M.; Wagner, A. R.; and Passonneau, R. J.\n\n\n \n\n\n\n In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6767–6780, Abu Dhabi, 2022. 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 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{zare_pomdp_2022,\n\taddress = {Abu Dhabi},\n\ttitle = {A {POMDP} {Dialogue} {Policy} with 3-way {Grounding} and {Adaptive} {Sensing} for {Learning} through {Communication}},\n\turl = {https://aclanthology.org/2022.findings-emnlp.504},\n\tabstract = {Agents to assist with rescue, surgery, and similar activities could collaborate better with humans if they could learn new strategic behaviors through communication. We introduce a novel POMDP dialogue policy for learning from people. The policy has 3-way grounding of language in the shared physical context, the dialogue context, and persistent knowledge. It can learn distinct but related games, and can continue learning across dialogues for complex games. A novel sensing component supports adaptation to information-sharing differences across people. The single policy performs bet- ter than oracle policies customized to specific games and information behavior.},\n\tbooktitle = {Findings of the {Association} for {Computational} {Linguistics}: {EMNLP} 2022},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Zare, Maryam and Wagner, Alan R. and Passonneau, Rebecca J.},\n\tyear = {2022},\n\tpages = {6767--6780},\n}\n\n
\n
\n\n\n
\n Agents to assist with rescue, surgery, and similar activities could collaborate better with humans if they could learn new strategic behaviors through communication. We introduce a novel POMDP dialogue policy for learning from people. The policy has 3-way grounding of language in the shared physical context, the dialogue context, and persistent knowledge. It can learn distinct but related games, and can continue learning across dialogues for complex games. A novel sensing component supports adaptation to information-sharing differences across people. The single policy performs bet- ter than oracle policies customized to specific games and information behavior.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n A Database of Multimodal Data to Construct a Simulated Dialogue Partner with Varying Degrees of Cognitive Health.\n \n \n \n\n\n \n Pan, R.; Liu, Z.; Yuan, F.; Zare, M.; Zhao, X.; and Passonneau, R. J.\n\n\n \n\n\n\n In Proceedings of the RaPID Workshop - Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments, Marseilles, June 2022. 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{pan_database_2022,\n\taddress = {Marseilles},\n\ttitle = {A {Database} of {Multimodal} {Data} to {Construct} a {Simulated} {Dialogue} {Partner} with {Varying} {Degrees} of {Cognitive} {Health}},\n\tabstract = {An assistive robot that could communicate with dementia patients would have great social benefit. An assistive robot Pepper has been designed to administer Referential Communication Tasks (RCTs) to human subjects without dementia as a step towards an agent to administer RCTs to dementia patients, potentially for earlier diagnosis. Currently, Pepper follows a rigid RCT script, which affects the user experience. We aim to replace Pepper’s RCT script with a dialogue management approach, to generate more natural interactions with RCT subjects. A Partially Observable Markov Decision Process (POMDP) dialogue policy will be trained using reinforcement learning, using simulated dialogue partners. This paper describes two RCT datasets and a methodology for their use in creating a database that the simulators can access for training the POMDP policies.},\n\tbooktitle = {Proceedings of the {RaPID} {Workshop} - {Resources} and {ProcessIng} of linguistic, para-linguistic and extra-linguistic {Data} from people with various forms of cognitive/psychiatric/developmental impairments},\n\tpublisher = {European Language Resources Association},\n\tauthor = {Pan, Ruihao and Liu, Ziming and Yuan, Fengpei and Zare, Maryam and Zhao, Xiaopeng and Passonneau, Rebecca J.},\n\tmonth = jun,\n\tyear = {2022},\n}\n\n
\n
\n\n\n
\n An assistive robot that could communicate with dementia patients would have great social benefit. An assistive robot Pepper has been designed to administer Referential Communication Tasks (RCTs) to human subjects without dementia as a step towards an agent to administer RCTs to dementia patients, potentially for earlier diagnosis. Currently, Pepper follows a rigid RCT script, which affects the user experience. We aim to replace Pepper’s RCT script with a dialogue management approach, to generate more natural interactions with RCT subjects. A Partially Observable Markov Decision Process (POMDP) dialogue policy will be trained using reinforcement learning, using simulated dialogue partners. This paper describes two RCT datasets and a methodology for their use in creating a database that the simulators can access for training the POMDP policies.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning.\n \n \n \n \n\n\n \n Das, S. S. S.; Katiyar, A.; Passonneau, R.; and Zhang, R.\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 6338–6353, Dublin, Ireland, 2022. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"CONTaiNER: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 
@inproceedings{das_container_2022,\n\taddress = {Dublin, Ireland},\n\ttitle = {{CONTaiNER}: {Few}-{Shot} {Named} {Entity} {Recognition} via {Contrastive} {Learning}},\n\tshorttitle = {{CONTaiNER}},\n\turl = {https://aclanthology.org/2022.acl-long.439},\n\tdoi = {10.18653/v1/2022.acl-long.439},\n\tlanguage = {en},\n\turldate = {2023-01-27},\n\tbooktitle = {Proceedings of the 60th {Annual} {Meeting} of the {Association} for {Computational} {Linguistics} ({Volume} 1: {Long} {Papers})},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Das, Sarkar Snigdha Sarathi and Katiyar, Arzoo and Passonneau, Rebecca and Zhang, Rui},\n\tyear = {2022},\n\tpages = {6338--6353},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Foundations for AI-Assisted Formative Assessment Feedback for Short-Answer Tasks in Large-Enrollment Classes.\n \n \n \n \n\n\n \n Lloyd, S.; Beckman, Matthew D.; Pearl, Dennis K.; Passonneau, Rebecca J.; Li, Zhaohui; and Wang, Zekun\n\n\n \n\n\n\n In Rosario, Argentina, September 2022. \n \n\n\n\n
\n\n\n\n \n \n \"FoundationsPaper\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{lloyd_susan_foundations_2022,\n\taddress = {Rosario, Argentina},\n\ttitle = {Foundations for {AI}-{Assisted} {Formative} {Assessment} {Feedback} for {Short}-{Answer} {Tasks} in {Large}-{Enrollment} {Classes}},\n\turl = {https://causeweb.org/cause/ecots/ecots22/program/posters/th-03},\n\tabstract = {Research suggests “write-to-learn” tasks improve learning outcomes, yet constructed-response methods of formative assessment become unwieldy with large class sizes. This study evaluates natural language processing algorithms to assist this aim. Six short-answer tasks completed by 1,935 students were scored by several human raters using a detailed rubric and an algorithm. Results indicate substantial inter-rater agreement using quadratic weighted kappa for rater pairs (each QWK {\\textgreater} 0.74) and group consensus (Fleiss’ Kappa = 0.68). Additionally, intra-rater agreement was estimated for one rater who had scored 188 responses seven years prior (QWK = 0.89). With compelling rater agreement, the study then pilots cluster analysis of response text toward enabling instructors to ascribe meaning to clusters as a means for scalable formative assessment.},\n\tauthor = {Lloyd, Susan and {Beckman, Matthew D.} and {Pearl, Dennis K.} and {Passonneau, Rebecca J.} and {Li, Zhaohui} and {Wang, Zekun}},\n\tmonth = sep,\n\tyear = {2022},\n}\n\n
\n
\n\n\n
\n Research suggests “write-to-learn” tasks improve learning outcomes, yet constructed-response methods of formative assessment become unwieldy with large class sizes. This study evaluates natural language processing algorithms to assist this aim. Six short-answer tasks completed by 1,935 students were scored by several human raters using a detailed rubric and an algorithm. Results indicate substantial inter-rater agreement using quadratic weighted kappa for rater pairs (each QWK \\textgreater 0.74) and group consensus (Fleiss’ Kappa = 0.68). Additionally, intra-rater agreement was estimated for one rater who had scored 188 responses seven years prior (QWK = 0.89). With compelling rater agreement, the study then pilots cluster analysis of response text toward enabling instructors to ascribe meaning to clusters as a means for scalable formative assessment.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Automated Support to Scaffold Students’ Written Explanations in Science.\n \n \n \n \n\n\n \n Singh, P.; Passonneau, R. J.; Wasih, M.; Cang, X.; Kim, C.; and Puntambekar, S.\n\n\n \n\n\n\n In Rodrigo, M. M.; Matsuda, N.; Cristea, A. I.; and Dimitrova, V., editor(s), Artificial Intelligence in Education, volume 13355, pages 660–665. Springer International Publishing, Cham, 2022.\n Series Title: Lecture Notes in Computer Science\n\n\n\n
\n\n\n\n \n \n \"AutomatedPaper\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 
@incollection{rodrigo_automated_2022,\n\taddress = {Cham},\n\ttitle = {Automated {Support} to {Scaffold} {Students}’ {Written} {Explanations} in {Science}},\n\tvolume = {13355},\n\tisbn = {978-3-031-11643-8 978-3-031-11644-5},\n\turl = {https://link.springer.com/10.1007/978-3-031-11644-5_64},\n\tlanguage = {en},\n\turldate = {2022-10-25},\n\tbooktitle = {Artificial {Intelligence} in {Education}},\n\tpublisher = {Springer International Publishing},\n\tauthor = {Singh, Purushartha and Passonneau, Rebecca J. and Wasih, Mohammad and Cang, Xuesong and Kim, ChanMin and Puntambekar, Sadhana},\n\teditor = {Rodrigo, Maria Mercedes and Matsuda, Noburu and Cristea, Alexandra I. and Dimitrova, Vania},\n\tyear = {2022},\n\tdoi = {10.1007/978-3-031-11644-5_64},\n\tnote = {Series Title: Lecture Notes in Computer Science},\n\tpages = {660--665},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Design of Real-time Scaffolding of Middle School Science Writing Using Automated Techniques.\n \n \n \n\n\n \n Singh, P.; Gnesdilow, D.; Cang, X.; Baker, S.; Goss, W.; Kim, C.; Passonneau, R. J.; and Puntambekar, S.\n\n\n \n\n\n\n In 2022. International Society of the Learning Sciences\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_design_2022,\n\ttitle = {Design of {Real}-time {Scaffolding} of {Middle} {School} {Science} {Writing} {Using} {Automated} {Techniques}},\n\tabstract = {Science writing skills depend on a student’s ability to co-ordinate conceptual understanding of science with the ability to articulate ideas independently, and to distinguish between gradations of importance in ideas. Real-time scaffolding of student writing during and immediately after the writing process could ease the cognitive burden of learning to co-ordinate these skills and enhance student learning of science. This paper presents a design process for automated support of real-time scaffolding of middle school students’ science explanations. We describe our adaptation of an existing tool for automatic content assessment to align more closely with a rubric, and our reliance on data mining of historical examples of middle school science writing. On a reserved test set of semi-synthetic examples of science explanations, the modified tool demonstrated high correlation with the manual rubric. We conclude the tool can support a wide range of design options for customized student feedback in real time.},\n\tpublisher = {International Society of the Learning Sciences},\n\tauthor = {Singh, Purushartha and Gnesdilow, Dana and Cang, Xuesong and Baker, Samantha and Goss, William and Kim, ChanMin and Passonneau, Rebecca J. and Puntambekar, Sadhana},\n\tyear = {2022},\n}\n\n
\n
\n\n\n
\n Science writing skills depend on a student’s ability to co-ordinate conceptual understanding of science with the ability to articulate ideas independently, and to distinguish between gradations of importance in ideas. Real-time scaffolding of student writing during and immediately after the writing process could ease the cognitive burden of learning to co-ordinate these skills and enhance student learning of science. This paper presents a design process for automated support of real-time scaffolding of middle school students’ science explanations. We describe our adaptation of an existing tool for automatic content assessment to align more closely with a rubric, and our reliance on data mining of historical examples of middle school science writing. On a reserved test set of semi-synthetic examples of science explanations, the modified tool demonstrated high correlation with the manual rubric. We conclude the tool can support a wide range of design options for customized student feedback in real time.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2021\n \n \n (5)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Automated Assessment of Quality and Coverage of Ideas in Students’ Source-Based Writing.\n \n \n \n\n\n \n Gao, Y.; Huang, T.; and Passonneau, R. J.\n\n\n \n\n\n\n In Proceedings of the International Conference on Artificial Intelligence in Education, pages 465–470, Utrecht, The Netherlands, 2021. Springer International Publishing\n \n\n\n\n
\n\n\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 \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{gao_automated_2021,\n\taddress = {Utrecht, The Netherlands},\n\ttitle = {Automated {Assessment} of {Quality} and {Coverage} of {Ideas} in {Students}’ {Source}-{Based} {Writing}},\n\tdoi = {0.1007/978-3-030-78270-2_82},\n\tabstract = {Source-based writing is an important academic skill in higher education, as it helps instructors evaluate students' understanding of subject matter. To assess the potential for supporting instructors' grading, we design an automated assessment tool for students' source-based summaries with natural language processing techniques. It includes a special-purpose parser that decomposes the sentences into clauses, a pre-trained semantic representation method, a novel algorithm that allocates ideas into weighted content units and another algorithm for scoring students' writing. We present results on three sets of student writing in higher education: two sets of STEM student writing samples and a set of reasoning sections of case briefs from a law school preparatory course. We show that this tool achieves promising results by correlating well with reliable human rubrics, and by helping instructors identify issues in grades they assign. We then discuss limitations and two improvements: a neural model that learns to decompose complex sentences into simple sentences, and a distinct model that learns a latent representation.},\n\tbooktitle = {Proceedings of the {International} {Conference} on {Artificial} {Intelligence} in {Education}},\n\tpublisher = {Springer International Publishing},\n\tauthor = {Gao, Yanjun and Huang, Ting-Hao and Passonneau, Rebecca J.},\n\tyear = {2021},\n\tpages = {465--470},\n}\n\n
\n
\n\n\n
\n Source-based writing is an important academic skill in higher education, as it helps instructors evaluate students' understanding of subject matter. To assess the potential for supporting instructors' grading, we design an automated assessment tool for students' source-based summaries with natural language processing techniques. It includes a special-purpose parser that decomposes the sentences into clauses, a pre-trained semantic representation method, a novel algorithm that allocates ideas into weighted content units and another algorithm for scoring students' writing. We present results on three sets of student writing in higher education: two sets of STEM student writing samples and a set of reasoning sections of case briefs from a law school preparatory course. We show that this tool achieves promising results by correlating well with reliable human rubrics, and by helping instructors identify issues in grades they assign. We then discuss limitations and two improvements: a neural model that learns to decompose complex sentences into simple sentences, and a distinct model that learns a latent representation.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Analytical Techniques for Developing Argumentative Writing in STEM: A Pilot Study.\n \n \n \n \n\n\n \n Davies, P. M.; Passonneau, R. J.; Muresan, S.; and Gao, Y.\n\n\n \n\n\n\n IEEE Transactions on Education,1–11. 2021.\n \n\n\n\n
\n\n\n\n \n \n \"AnalyticalPaper\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 
@article{davies_analytical_2021,\n\ttitle = {Analytical {Techniques} for {Developing} {Argumentative} {Writing} in {STEM}: {A} {Pilot} {Study}},\n\tissn = {0018-9359, 1557-9638},\n\tshorttitle = {Analytical {Techniques} for {Developing} {Argumentative} {Writing} in {STEM}},\n\turl = {https://ieeexplore.ieee.org/document/9566612/},\n\tdoi = {10.1109/TE.2021.3116202},\n\turldate = {2022-04-19},\n\tjournal = {IEEE Transactions on Education},\n\tauthor = {Davies, Patricia Marybelle and Passonneau, Rebecca Jane and Muresan, Smaranda and Gao, Yanjun},\n\tyear = {2021},\n\tpages = {1--11},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Learning Clause Representation from Dependency-Anchor Graph for Connective Prediction.\n \n \n \n \n\n\n \n Gao, Y.; Huang, T.; and Passonneau, R. J.\n\n\n \n\n\n\n In Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15), pages 54–66, Mexico City, Mexico, 2021. 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 \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{gao_learning_2021,\n\taddress = {Mexico City, Mexico},\n\ttitle = {Learning {Clause} {Representation} from {Dependency}-{Anchor} {Graph} for {Connective} {Prediction}},\n\turl = {https://aclanthology.org/2021.textgraphs-1.6},\n\tdoi = {10.18653/v1/2021.textgraphs-1.6},\n\tlanguage = {en},\n\turldate = {2022-04-19},\n\tbooktitle = {Proceedings of the {Fifteenth} {Workshop} on {Graph}-{Based} {Methods} for {Natural} {Language} {Processing} ({TextGraphs}-15)},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Gao, Yanjun and Huang, Ting-Hao and Passonneau, Rebecca J.},\n\tyear = {2021},\n\tpages = {54--66},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences.\n \n \n \n \n\n\n \n Gao, Y.; Huang, T.; and Passonneau, R. J.\n\n\n \n\n\n\n In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3919–3931, Online, 2021. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"ABCD: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 
@inproceedings{gao_abcd_2021,\n\taddress = {Online},\n\ttitle = {{ABCD}: {A} {Graph} {Framework} to {Convert} {Complex} {Sentences} to a {Covering} {Set} of {Simple} {Sentences}},\n\tshorttitle = {{ABCD}},\n\turl = {https://aclanthology.org/2021.acl-long.303},\n\tdoi = {10.18653/v1/2021.acl-long.303},\n\tlanguage = {en},\n\turldate = {2022-04-19},\n\tbooktitle = {Proceedings of the 59th {Annual} {Meeting} of the {Association} for {Computational} {Linguistics} and the 11th {International} {Joint} {Conference} on {Natural} {Language} {Processing} ({Volume} 1: {Long} {Papers})},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Gao, Yanjun and Huang, Ting-Hao and Passonneau, Rebecca J.},\n\tyear = {2021},\n\tpages = {3919--3931},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Semantic Feature-Wise Transformation Relation Network for Automatic Short Answer Grading.\n \n \n \n \n\n\n \n Li, Z.; Tomar, Y.; and Passonneau, R. J.\n\n\n \n\n\n\n In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6030–6040, Online and Punta Cana, Dominican Republic, 2021. Association for Computational Linguistics\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 \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{li_semantic_2021,\n\taddress = {Online and Punta Cana, Dominican Republic},\n\ttitle = {A {Semantic} {Feature}-{Wise} {Transformation} {Relation} {Network} for {Automatic} {Short} {Answer} {Grading}},\n\turl = {https://aclanthology.org/2021.emnlp-main.487},\n\tdoi = {10.18653/v1/2021.emnlp-main.487},\n\tlanguage = {en},\n\turldate = {2022-04-19},\n\tbooktitle = {Proceedings of the 2021 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Li, Zhaohui and Tomar, Yajur and Passonneau, Rebecca J.},\n\tyear = {2021},\n\tpages = {6030--6040},\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2020\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Dialogue Policies for Learning Board Games through Multimodal Communication.\n \n \n \n\n\n \n Zare, M.; Ayub, A.; Liu, A.; Sudhakara, S.; Wagner, A.; and Passonneau, R. J.\n\n\n \n\n\n\n In 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue, Boise, Idaha, 2020. 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{zare_dialogue_2020,\n\taddress = {Boise, Idaha},\n\ttitle = {Dialogue {Policies} for {Learning} {Board} {Games} through {Multimodal} {Communication}},\n\tabstract = {This paper presents MDP policy learning for agents to learn strategic behavior–how to play board games–during multimodal dialogues. Policies are trained offline in simulation, with dialogues carried out in a formal language. The agent has a temporary belief state for the dialogue, and a persistent knowledge store represented as an extensive-form game tree. How well the agent learns a new game from a dialogue with a simulated partner is evaluated by how well it plays the game, given its dialogue-final knowledge state. During policy training, we control for the simulated dialogue partner’s level of informativeness in responding to questions. The agent learns best when its trained policy matches the current dialogue partner’s informativeness. We also present a novel data collection for training natural language modules. Human subjects who engaged in dialogues with a baseline system rated the sys- tem’s language skills as above average. Further, results confirm that human dialogue par ners also vary in their informativeness.},\n\tbooktitle = {21st {Annual} {Meeting} of the {Special} {Interest} {Group} on {Discourse} and {Dialogue}},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Zare, Maryam and Ayub, Ali and Liu, Aishan and Sudhakara, Sweekar and Wagner, Alan and Passonneau, Rebecca J.},\n\tyear = {2020},\n}\n\n
\n
\n\n\n
\n This paper presents MDP policy learning for agents to learn strategic behavior–how to play board games–during multimodal dialogues. Policies are trained offline in simulation, with dialogues carried out in a formal language. The agent has a temporary belief state for the dialogue, and a persistent knowledge store represented as an extensive-form game tree. How well the agent learns a new game from a dialogue with a simulated partner is evaluated by how well it plays the game, given its dialogue-final knowledge state. During policy training, we control for the simulated dialogue partner’s level of informativeness in responding to questions. The agent learns best when its trained policy matches the current dialogue partner’s informativeness. We also present a novel data collection for training natural language modules. Human subjects who engaged in dialogues with a baseline system rated the sys- tem’s language skills as above average. Further, results confirm that human dialogue par ners also vary in their informativeness.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2019\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Automated Pyramid Summarization Evaluation.\n \n \n \n \n\n\n \n Gao, Y.; Sun, C.; and Passonneau, R. J.\n\n\n \n\n\n\n In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 404–418, Hong Kong, China, 2019. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"AutomatedPaper\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 
@inproceedings{gao_automated_2019,\n\taddress = {Hong Kong, China},\n\ttitle = {Automated {Pyramid} {Summarization} {Evaluation}},\n\turl = {https://www.aclweb.org/anthology/K19-1038},\n\tdoi = {10.18653/v1/K19-1038},\n\tlanguage = {en},\n\turldate = {2022-04-21},\n\tbooktitle = {Proceedings of the 23rd {Conference} on {Computational} {Natural} {Language} {Learning} ({CoNLL})},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Gao, Yanjun and Sun, Chen and Passonneau, Rebecca J.},\n\tyear = {2019},\n\tpages = {404--418},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Rubric Reliability and Annotation of Content and Argument in Source-Based Argument Essays.\n \n \n \n \n\n\n \n Gao, Y.; Driban, A.; Xavier McManus, B.; Musi, E.; Davies, P.; Muresan, S.; and Passonneau, R. J.\n\n\n \n\n\n\n In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 507–518, Florence, Italy, 2019. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"RubricPaper\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 
@inproceedings{gao_rubric_2019,\n\taddress = {Florence, Italy},\n\ttitle = {Rubric {Reliability} and {Annotation} of {Content} and {Argument} in {Source}-{Based} {Argument} {Essays}},\n\turl = {https://www.aclweb.org/anthology/W19-4452},\n\tdoi = {10.18653/v1/W19-4452},\n\tlanguage = {en},\n\turldate = {2022-04-19},\n\tbooktitle = {Proceedings of the {Fourteenth} {Workshop} on {Innovative} {Use} of {NLP} for {Building} {Educational} {Applications}},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Gao, Yanjun and Driban, Alex and Xavier McManus, Brennan and Musi, Elena and Davies, Patricia and Muresan, Smaranda and Passonneau, Rebecca J.},\n\tyear = {2019},\n\tpages = {507--518},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Show Me How to Win: A Robot that Uses Dialog Management to Learn from Demonstrations.\n \n \n \n \n\n\n \n Zare, M.; Ayub, A.; Wagner, A. R.; and Passonneau, R. J.\n\n\n \n\n\n\n In Fourth Games and Natural Language Processing Workshop (GAMNLP-19), San Luis Obispo, CA, 2019. \n \n\n\n\n
\n\n\n\n \n \n \"ShowPaper\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{zare_show_2019,\n\taddress = {San Luis Obispo, CA},\n\ttitle = {Show {Me} {How} to {Win}: {A} {Robot} that {Uses} {Dialog} {Management} to {Learn} from {Demonstrations}.},\n\turl = {https://dl.acm.org/doi/10.1145/3337722.3341866},\n\tbooktitle = {Fourth {Games} and {Natural} {Language} {Processing} {Workshop} ({GAMNLP}-19)},\n\tauthor = {Zare, Maryam and Ayub, Ali and Wagner, Alan R. and Passonneau, Rebecca J.},\n\tyear = {2019},\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2018\n \n \n (6)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n PyrEval: An Automated Method for Summary Content Analysis.\n \n \n \n \n\n\n \n Gao, Y.; Warner, A.; and Passonneau, R. J.\n\n\n \n\n\n\n In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan, May 2018. European Language Resource Association\n \n\n\n\n
\n\n\n\n \n \n \"PyrEval: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{gao_pyreval_2018,\n\taddress = {Miyazaki, Japan},\n\ttitle = {{PyrEval}: {An} {Automated} {Method} for {Summary} {Content} {Analysis}},\n\turl = {http://www.lrec-conf.org/proceedings/lrec2018/pdf/1096.pdf},\n\tabstract = {The pyramid method is a content analysis approach in automatic summarization evaluation for manual construction of a content model from reference summaries, and manual scoring of unseen summaries with the pyramid model. PyrEval automates the manual pyramid method. PyrEval uses low-dimension distributional semantics to represent phrase meanings, and a new algorithm, EDUA (Emergent Discovery of Units of Attraction), to solve a set cover problem to construct the content model from vectorized phrases. Because the vectors are pretrained, and EDUA is an efficient greedy algorithm, PyrEval can apply pyramid content evaluation with no retraining, and in excellent time. Moreover, PyrEval has been tested on many datasets derived from humans and machine generated summaries, and shown good performance on both.},\n\tbooktitle = {Proceedings of the {Eleventh} {International} {Conference} on {Language} {Resources} and {Evaluation} ({LREC} 2018)},\n\tpublisher = {European Language Resource Association},\n\tauthor = {Gao, Yanjun and Warner, Andrew and Passonneau, Rebecca J.},\n\tmonth = may,\n\tyear = {2018},\n}\n\n
\n
\n\n\n
\n The pyramid method is a content analysis approach in automatic summarization evaluation for manual construction of a content model from reference summaries, and manual scoring of unseen summaries with the pyramid model. PyrEval automates the manual pyramid method. PyrEval uses low-dimension distributional semantics to represent phrase meanings, and a new algorithm, EDUA (Emergent Discovery of Units of Attraction), to solve a set cover problem to construct the content model from vectorized phrases. Because the vectors are pretrained, and EDUA is an efficient greedy algorithm, PyrEval can apply pyramid content evaluation with no retraining, and in excellent time. Moreover, PyrEval has been tested on many datasets derived from humans and machine generated summaries, and shown good performance on both.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Automated Content Analysis: A Case Study of Computer Science Student Summaries.\n \n \n \n \n\n\n \n Gao, Y.; M.Davies, P.; and Passonneau, R. J.\n\n\n \n\n\n\n In Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 264–272, New Orleans, Louisiana, 2018. Association for Computational Linguistics\n \n\n\n\n
\n\n\n\n \n \n \"AutomatedPaper\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 
@inproceedings{gao_automated_2018,\n\taddress = {New Orleans, Louisiana},\n\ttitle = {Automated {Content} {Analysis}: {A} {Case} {Study} of {Computer} {Science} {Student} {Summaries}},\n\tshorttitle = {Automated {Content} {Analysis}},\n\turl = {http://aclweb.org/anthology/W18-0531},\n\tdoi = {10.18653/v1/W18-0531},\n\tlanguage = {en},\n\turldate = {2022-04-19},\n\tbooktitle = {Proceedings of the {Thirteenth} {Workshop} on {Innovative} {Use} of {NLP} for           {Building} {Educational} {Applications}},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Gao, Yanjun and M.Davies, Patricia and Passonneau, Rebecca J.},\n\tyear = {2018},\n\tpages = {264--272},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Testing a Knowledge Inquiry System on Question Answering Tasks.\n \n \n \n\n\n \n Zafeiroudi, K. D.; Eckman, L.; and Passonneau, R. J.\n\n\n \n\n\n\n In Joint Proceedings of ISWC 2018 Workshops SemDeep-4 and NLIWoD-4., Monterey, CA, October 2018. \n Best Paper.\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{zafeiroudi_testing_2018,\n\taddress = {Monterey, CA},\n\ttitle = {Testing a {Knowledge} {Inquiry} {System} on\nQuestion {Answering} {Tasks}},\n\tabstract = {Question-Answering systems enable users to retrieve answers to factual questions from various kinds of knowledge sources, but do not address how to respond cooperatively. We present InK, an initial inquiry system for RDF knowledge graphs that aims to return relevant responses, even when an answer cannot be found. It assembles knowledge\nrelevant to the entities mentioned in the question without translating the input question into a query language. A user study indicates responses are found to be intelligible and relevant. Evaluation of questions with known answers gives high recall of 0.70 averaged on three QA datasets.},\n\tbooktitle = {Joint {Proceedings} of {ISWC} 2018 {Workshops} {SemDeep}-4 and {NLIWoD}-4.},\n\tauthor = {Zafeiroudi, Kyriaki D. and Eckman, Leah and Passonneau, Rebecca J.},\n\tmonth = oct,\n\tyear = {2018},\n\tnote = {Best Paper.},\n}\n\n
\n
\n\n\n
\n Question-Answering systems enable users to retrieve answers to factual questions from various kinds of knowledge sources, but do not address how to respond cooperatively. We present InK, an initial inquiry system for RDF knowledge graphs that aims to return relevant responses, even when an answer cannot be found. It assembles knowledge relevant to the entities mentioned in the question without translating the input question into a query language. A user study indicates responses are found to be intelligible and relevant. Evaluation of questions with known answers gives high recall of 0.70 averaged on three QA datasets.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Wise Crowd Content Assessment and Educational Rubrics.\n \n \n \n \n\n\n \n Passonneau, R. J.; Poddar, A.; Gite, G.; Krivokapic, A.; Yang, Q.; and Perin, D.\n\n\n \n\n\n\n International Journal of Artificial Intelligence in Education, 28(1): 29–55. March 2018.\n \n\n\n\n
\n\n\n\n \n \n \"WisePaper\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 \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{passonneau_wise_2018,\n\tseries = {Special {Issue} on {Multidisciplinary} {Approaches} to {AI} and {Education} for {Reading} and {Writing}},\n\ttitle = {Wise {Crowd} {Content} {Assessment} and {Educational} {Rubrics}},\n\tvolume = {28},\n\tissn = {1560-4292},\n\tshorttitle = {Wise {Crowd} {Content} {Assessment}},\n\turl = {https://link.springer.com/article/10.1007/s40593-016-0128-6#citeas},\n\tdoi = {https://doi.org/10.1007/s40593-016-0128-6},\n\tabstract = {Development of reliable rubrics for educational intervention studies that address reading and writing skills is labor-intensive, and could benefit from an automated approach. We compare a main ideas rubric used in a successful writing intervention study to a highly reliable wise-crowd content assessment method developed to evaluate machine-generated summaries. The ideas in the educational rubric were extracted from a source text that students were asked to summarize. The wise-crowd content assessment model is derived from summaries written by an independent group of proficient students who read the same source text, and followed the same instructions to write their summaries. The resulting content model includes a ranking over the derived content units. All main ideas in the rubric appear prominently in the wise-crowd content model. We present two methods that automate the content assessment. Scores based on the wise-crowd content assessment, both manual and automated, have high correlations with the main ideas rubric. The automated content assessment methods have several advantages over related methods, including high correlations with corresponding manual scores, a need for only half a dozen models instead of hundreds, and interpretable scores that independently assess content quality and coverage.},\n\tnumber = {1},\n\tjournal = {International Journal of Artificial Intelligence in Education},\n\tauthor = {Passonneau, Rebecca J. and Poddar, Ananya and Gite, Gaurav and Krivokapic, Alisa and Yang, Qian and Perin, Dolores},\n\tmonth = mar,\n\tyear = {2018},\n\tpages = {29--55},\n}\n\n
\n
\n\n\n
\n Development of reliable rubrics for educational intervention studies that address reading and writing skills is labor-intensive, and could benefit from an automated approach. We compare a main ideas rubric used in a successful writing intervention study to a highly reliable wise-crowd content assessment method developed to evaluate machine-generated summaries. The ideas in the educational rubric were extracted from a source text that students were asked to summarize. The wise-crowd content assessment model is derived from summaries written by an independent group of proficient students who read the same source text, and followed the same instructions to write their summaries. The resulting content model includes a ranking over the derived content units. All main ideas in the rubric appear prominently in the wise-crowd content model. We present two methods that automate the content assessment. Scores based on the wise-crowd content assessment, both manual and automated, have high correlations with the main ideas rubric. The automated content assessment methods have several advantages over related methods, including high correlations with corresponding manual scores, a need for only half a dozen models instead of hundreds, and interpretable scores that independently assess content quality and coverage.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Prediction of a hotspot pattern in keyword search results.\n \n \n \n\n\n \n Gao, J.; Radeva, A.; Shen, C.; Wang, S.; Wang, Q.; and Passonneau, R. J.\n\n\n \n\n\n\n Computer Speech & Language, 48: 80–102. March 2018.\n \n\n\n\n
\n\n\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 \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{gao_prediction_2018,\n\ttitle = {Prediction of a hotspot pattern in keyword search results},\n\tvolume = {48},\n\tdoi = {https://doi.org/10.1016/j.csl.2017.10.005},\n\tabstract = {This paper identifies and models a phenomenon observed across low-resource languages in keyword search results from speech retrieval systems where the speech recognition has high error rate, due to very limited training data. High confidence correct detections (hccds) of keywords are rare, yet often succeed one another closely in time. We refer to these close sequences of hccds as keyword hotspots. The ability to predict keyword hotspots could support speech retrieval, and provide new insights into the behavior of speech recognition systems. We treat hotspot prediction as a binary classification task on all word-sized time intervals in an audio file of a telephone conversation, using prosodic features as predictors. Rare events that follow this pattern are often modeled as a self-exciting point process (sepp), meaning the occurrence of a rare event excites a following one. To label successive points in time as occurring within a hotspot or not, we fit a sepp function to the distribution of hccds in the keyword search output. Two major learning challenges are that the size of the positive class is very small, and the training and test data have dissimilar distributions. To address these challenges, we develop a novel data selection framework that chooses training data with good generalization properties. Results exhibit superior generalization performance.},\n\tjournal = {Computer Speech \\& Language},\n\tauthor = {Gao, Jie and Radeva, Axinia and Shen, Chuyao and Wang, Shiqi and Wang, Qianbo and Passonneau, Rebecca J.},\n\tmonth = mar,\n\tyear = {2018},\n\tpages = {80--102},\n}\n\n
\n
\n\n\n
\n This paper identifies and models a phenomenon observed across low-resource languages in keyword search results from speech retrieval systems where the speech recognition has high error rate, due to very limited training data. High confidence correct detections (hccds) of keywords are rare, yet often succeed one another closely in time. We refer to these close sequences of hccds as keyword hotspots. The ability to predict keyword hotspots could support speech retrieval, and provide new insights into the behavior of speech recognition systems. We treat hotspot prediction as a binary classification task on all word-sized time intervals in an audio file of a telephone conversation, using prosodic features as predictors. Rare events that follow this pattern are often modeled as a self-exciting point process (sepp), meaning the occurrence of a rare event excites a following one. To label successive points in time as occurring within a hotspot or not, we fit a sepp function to the distribution of hccds in the keyword search output. Two major learning challenges are that the size of the positive class is very small, and the training and test data have dissimilar distributions. To address these challenges, we develop a novel data selection framework that chooses training data with good generalization properties. Results exhibit superior generalization performance.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Knowledge Inquiry for Information Foraging.\n \n \n \n\n\n \n Zafeiroudi, K. D.; and Passonneau, R. J.\n\n\n \n\n\n\n In Pensacola, FL, November 2018. \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{zafeiroudi_knowledge_2018,\n\taddress = {Pensacola, FL},\n\ttitle = {Knowledge {Inquiry} for {Information} {Foraging}},\n\tabstract = {Human analysts have a vital role in the task of sensemaking, the process of extracting\ninformation to reach conclusions and make decisions. Question-Answering (QA) is an existing natural language processing application that would appear to be relevant to the analyst’s task, given information needs to address in a structured knowledge source. Standard QA systems, however, assume an input question can be interpreted in isolation, meaning that there is a single translation of language to a structured query, and that there is a unique correct answer.\nWe assume that a more appropriate tool for an analyst would support open-ended exploration for relevant information from structured data sources, and would not commit too early to a single interpretation of the analyst’s question. We provide the capability to pose natural language questions to knowledge graphs in RDF format where information that is relevant to the question can be visualized, making the knowledge source more transparent to the user.\nThis paper presents InK, an inquiry system for knowledge graphs where the input is a NL natural language (NL) question and the output consists of knowledge assumed to be relevant to a general information need that motivates the question.},\n\tauthor = {Zafeiroudi, Kyriaki D. and Passonneau, Rebecca J.},\n\tmonth = nov,\n\tyear = {2018},\n}\n
\n
\n\n\n
\n Human analysts have a vital role in the task of sensemaking, the process of extracting information to reach conclusions and make decisions. Question-Answering (QA) is an existing natural language processing application that would appear to be relevant to the analyst’s task, given information needs to address in a structured knowledge source. Standard QA systems, however, assume an input question can be interpreted in isolation, meaning that there is a single translation of language to a structured query, and that there is a unique correct answer. We assume that a more appropriate tool for an analyst would support open-ended exploration for relevant information from structured data sources, and would not commit too early to a single interpretation of the analyst’s question. We provide the capability to pose natural language questions to knowledge graphs in RDF format where information that is relevant to the question can be visualized, making the knowledge source more transparent to the user. This paper presents InK, an inquiry system for knowledge graphs where the input is a NL natural language (NL) question and the output consists of knowledge assumed to be relevant to a general information need that motivates the question.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2017\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Distractor Generation with Generative Adversarial Nets for Automatically Creating Fill-in-the-blank Questions.\n \n \n \n \n\n\n \n Liang, C.; Yang, X.; Wham, D.; Pursel, B.; Passonneau, R.; and Giles, C. L.\n\n\n \n\n\n\n In Proceedings of the Knowledge Capture Conference, pages 1–4, Austin TX USA, December 2017. ACM\n \n\n\n\n
\n\n\n\n \n \n \"DistractorPaper\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 
@inproceedings{liang_distractor_2017,\n\taddress = {Austin TX USA},\n\ttitle = {Distractor {Generation} with {Generative} {Adversarial} {Nets} for {Automatically} {Creating} {Fill}-in-the-blank {Questions}},\n\tisbn = {978-1-4503-5553-7},\n\turl = {https://dl.acm.org/doi/10.1145/3148011.3154463},\n\tdoi = {10.1145/3148011.3154463},\n\tlanguage = {en},\n\turldate = {2022-04-21},\n\tbooktitle = {Proceedings of the {Knowledge} {Capture} {Conference}},\n\tpublisher = {ACM},\n\tauthor = {Liang, Chen and Yang, Xiao and Wham, Drew and Pursel, Bart and Passonneau, Rebecca and Giles, C. Lee},\n\tmonth = dec,\n\tyear = {2017},\n\tpages = {1--4},\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2016\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n PEAK: Pyramid Evaluation via Automated Knowledge Extraction.\n \n \n \n \n\n\n \n Yang, Q.; de Melo, G.; and Passonneau, R. J.\n\n\n \n\n\n\n In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, Phoenix, AZ, February 2016. AAAI\n \n\n\n\n
\n\n\n\n \n \n \"PEAK: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{yang_peak:_2016,\n\taddress = {Phoenix, AZ},\n\ttitle = {{PEAK}: {Pyramid} {Evaluation} via {Automated} {Knowledge} {Extraction}},\n\turl = {https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12481/12007},\n\tabstract = {Evaluating the selection of content in a summary is important both for human-written summaries, which can be a useful\npedagogical tool for reading and writing skills, and machinegenerated summaries, which are increasingly being deployed\nin information management. The pyramid method assesses a summary by aggregating content units from the summaries of a wise crowd (a form of crowdsourcing). It has proven highly reliable but has largely depended on manual annotation. We propose PEAK, the first method to automatically\nassess summary content using the pyramid method that also generates the pyramid content models. PEAK relies on open information extraction and graph algorithms. The resulting scores correlate well with manually derived pyramid scores\non both human and machine summaries, opening up the possibility of wide-spread use in numerous applications.},\n\tbooktitle = {Proceedings of the {Thirtieth} {AAAI} {Conference} on {Artificial} {Intelligence}},\n\tpublisher = {AAAI},\n\tauthor = {Yang, Qian and de Melo, Gerard and Passonneau, Rebecca J.},\n\tmonth = feb,\n\tyear = {2016},\n}\n\n
\n
\n\n\n
\n Evaluating the selection of content in a summary is important both for human-written summaries, which can be a useful pedagogical tool for reading and writing skills, and machinegenerated summaries, which are increasingly being deployed in information management. The pyramid method assesses a summary by aggregating content units from the summaries of a wise crowd (a form of crowdsourcing). It has proven highly reliable but has largely depended on manual annotation. We propose PEAK, the first method to automatically assess summary content using the pyramid method that also generates the pyramid content models. PEAK relies on open information extraction and graph algorithms. The resulting scores correlate well with manually derived pyramid scores on both human and machine summaries, opening up the possibility of wide-spread use in numerous applications.\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);