Structured prediction models for RNN based sequence labeling in clinical text. Jagannatha, A. N. & Yu, H. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, volume 2016, pages 856–865, November, 2016. abstract bibtex Sequence labeling is a widely used method for named entity recognition and information extraction from unstructured natural language data. In clinical domain one major application of sequence labeling involves extraction of medical entities such as medication, indication, and side-effects from Electronic Health Record narratives. Sequence labeling in this domain, presents its own set of challenges and objectives. In this work we experimented with various CRF based structured learning models with Recurrent Neural Networks. We extend the previously studied LSTM-CRF models with explicit modeling of pairwise potentials. We also propose an approximate version of skip-chain CRF inference with RNN potentials. We use these methodologies for structured prediction in order to improve the exact phrase detection of various medical entities.
@inproceedings{jagannatha_structured_2016,
title = {Structured prediction models for {RNN} based sequence labeling in clinical text},
volume = {2016},
abstract = {Sequence labeling is a widely used method for named entity recognition and information extraction from unstructured natural language data. In clinical domain one major application of sequence labeling involves extraction of medical entities such as medication, indication, and side-effects from Electronic Health Record narratives. Sequence labeling in this domain, presents its own set of challenges and objectives. In this work we experimented with various CRF based structured learning models with Recurrent Neural Networks. We extend the previously studied LSTM-CRF models with explicit modeling of pairwise potentials. We also propose an approximate version of skip-chain CRF inference with RNN potentials. We use these methodologies for structured prediction in order to improve the exact phrase detection of various medical entities.},
language = {eng},
booktitle = {Proceedings of the {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}},
author = {Jagannatha, Abhyuday N. and Yu, Hong},
month = nov,
year = {2016},
pmid = {28004040 PMCID: PMC5167535},
keywords = {Computer Science - Computation and Language},
pages = {856--865},
}
Downloads: 0
{"_id":"GnvjEd4wYoP75Fj4r","bibbaseid":"jagannatha-yu-structuredpredictionmodelsforrnnbasedsequencelabelinginclinicaltext-2016","author_short":["Jagannatha, A. N.","Yu, H."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Structured prediction models for RNN based sequence labeling in clinical text","volume":"2016","abstract":"Sequence labeling is a widely used method for named entity recognition and information extraction from unstructured natural language data. In clinical domain one major application of sequence labeling involves extraction of medical entities such as medication, indication, and side-effects from Electronic Health Record narratives. Sequence labeling in this domain, presents its own set of challenges and objectives. In this work we experimented with various CRF based structured learning models with Recurrent Neural Networks. We extend the previously studied LSTM-CRF models with explicit modeling of pairwise potentials. We also propose an approximate version of skip-chain CRF inference with RNN potentials. We use these methodologies for structured prediction in order to improve the exact phrase detection of various medical entities.","language":"eng","booktitle":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":[{"propositions":[],"lastnames":["Jagannatha"],"firstnames":["Abhyuday","N."],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong"],"suffixes":[]}],"month":"November","year":"2016","pmid":"28004040 PMCID: PMC5167535","keywords":"Computer Science - Computation and Language","pages":"856–865","bibtex":"@inproceedings{jagannatha_structured_2016,\n\ttitle = {Structured prediction models for {RNN} based sequence labeling in clinical text},\n\tvolume = {2016},\n\tabstract = {Sequence labeling is a widely used method for named entity recognition and information extraction from unstructured natural language data. In clinical domain one major application of sequence labeling involves extraction of medical entities such as medication, indication, and side-effects from Electronic Health Record narratives. Sequence labeling in this domain, presents its own set of challenges and objectives. In this work we experimented with various CRF based structured learning models with Recurrent Neural Networks. We extend the previously studied LSTM-CRF models with explicit modeling of pairwise potentials. We also propose an approximate version of skip-chain CRF inference with RNN potentials. We use these methodologies for structured prediction in order to improve the exact phrase detection of various medical entities.},\n\tlanguage = {eng},\n\tbooktitle = {Proceedings of the {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}},\n\tauthor = {Jagannatha, Abhyuday N. and Yu, Hong},\n\tmonth = nov,\n\tyear = {2016},\n\tpmid = {28004040 PMCID: PMC5167535},\n\tkeywords = {Computer Science - Computation and Language},\n\tpages = {856--865},\n}\n\n","author_short":["Jagannatha, A. N.","Yu, H."],"key":"jagannatha_structured_2016","id":"jagannatha_structured_2016","bibbaseid":"jagannatha-yu-structuredpredictionmodelsforrnnbasedsequencelabelinginclinicaltext-2016","role":"author","urls":{},"keyword":["Computer Science - Computation and Language"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"http://fenway.cs.uml.edu/papers/pubs-all.bib","dataSources":["TqaA9miSB65nRfS5H"],"keywords":["computer science - computation and language"],"search_terms":["structured","prediction","models","rnn","based","sequence","labeling","clinical","text","jagannatha","yu"],"title":"Structured prediction models for RNN based sequence labeling in clinical text","year":2016}