@inproceedings{tao-etal-2019-effective,
title = "Effective Feature Representation for Clinical Text Concept Extraction",
author = "Tao, Yifeng and
Godefroy, Bruno and
Genthial, Guillaume and
Potts, Christopher",
editor = "Rumshisky, Anna and
Roberts, Kirk and
Bethard, Steven and
Naumann, Tristan",
booktitle = "Proceedings of the 2nd Clinical Natural Language Processing Workshop",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-1901",
doi = "10.18653/v1/W19-1901",
pages = "1--14",
abstract = "Crucial information about the practice of healthcare is recorded only in free-form text, which creates an enormous opportunity for high-impact NLP. However, annotated healthcare datasets tend to be small and expensive to obtain, which raises the question of how to make maximally efficient uses of the available data. To this end, we develop an LSTM-CRF model for combining unsupervised word representations and hand-built feature representations derived from publicly available healthcare ontologies. We show that this combined model yields superior performance on five datasets of diverse kinds of healthcare text (clinical, social, scientific, commercial). Each involves the labeling of complex, multi-word spans that pick out different healthcare concepts. We also introduce a new labeled dataset for identifying the treatment relations between drugs and diseases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tao-etal-2019-effective">
<titleInfo>
<title>Effective Feature Representation for Clinical Text Concept Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifeng</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Godefroy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Genthial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Potts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Crucial information about the practice of healthcare is recorded only in free-form text, which creates an enormous opportunity for high-impact NLP. However, annotated healthcare datasets tend to be small and expensive to obtain, which raises the question of how to make maximally efficient uses of the available data. To this end, we develop an LSTM-CRF model for combining unsupervised word representations and hand-built feature representations derived from publicly available healthcare ontologies. We show that this combined model yields superior performance on five datasets of diverse kinds of healthcare text (clinical, social, scientific, commercial). Each involves the labeling of complex, multi-word spans that pick out different healthcare concepts. We also introduce a new labeled dataset for identifying the treatment relations between drugs and diseases.</abstract>
<identifier type="citekey">tao-etal-2019-effective</identifier>
<identifier type="doi">10.18653/v1/W19-1901</identifier>
<location>
<url>https://aclanthology.org/W19-1901</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>1</start>
<end>14</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effective Feature Representation for Clinical Text Concept Extraction
%A Tao, Yifeng
%A Godefroy, Bruno
%A Genthial, Guillaume
%A Potts, Christopher
%Y Rumshisky, Anna
%Y Roberts, Kirk
%Y Bethard, Steven
%Y Naumann, Tristan
%S Proceedings of the 2nd Clinical Natural Language Processing Workshop
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota, USA
%F tao-etal-2019-effective
%X Crucial information about the practice of healthcare is recorded only in free-form text, which creates an enormous opportunity for high-impact NLP. However, annotated healthcare datasets tend to be small and expensive to obtain, which raises the question of how to make maximally efficient uses of the available data. To this end, we develop an LSTM-CRF model for combining unsupervised word representations and hand-built feature representations derived from publicly available healthcare ontologies. We show that this combined model yields superior performance on five datasets of diverse kinds of healthcare text (clinical, social, scientific, commercial). Each involves the labeling of complex, multi-word spans that pick out different healthcare concepts. We also introduce a new labeled dataset for identifying the treatment relations between drugs and diseases.
%R 10.18653/v1/W19-1901
%U https://aclanthology.org/W19-1901
%U https://doi.org/10.18653/v1/W19-1901
%P 1-14
Markdown (Informal)
[Effective Feature Representation for Clinical Text Concept Extraction](https://aclanthology.org/W19-1901) (Tao et al., ClinicalNLP 2019)
ACL