@inproceedings{joshi-etal-2019-comparison,
title = "A Comparison of Word-based and Context-based Representations for Classification Problems in Health Informatics",
author = "Joshi, Aditya and
Karimi, Sarvnaz and
Sparks, Ross and
Paris, Cecile and
MacIntyre, C Raina",
editor = "Demner-Fushman, Dina and
Cohen, Kevin Bretonnel and
Ananiadou, Sophia and
Tsujii, Junichi",
booktitle = "Proceedings of the 18th BioNLP Workshop and Shared Task",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5015",
doi = "10.18653/v1/W19-5015",
pages = "135--141",
abstract = "Distributed representations of text can be used as features when training a statistical classifier. These representations may be created as a composition of word vectors or as context-based sentence vectors. We compare the two kinds of representations (word versus context) for three classification problems: influenza infection classification, drug usage classification and personal health mention classification. For statistical classifiers trained for each of these problems, context-based representations based on ELMo, Universal Sentence Encoder, Neural-Net Language Model and FLAIR are better than Word2Vec, GloVe and the two adapted using the MESH ontology. There is an improvement of 2-4{\%} in the accuracy when these context-based representations are used instead of word-based representations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="joshi-etal-2019-comparison">
<titleInfo>
<title>A Comparison of Word-based and Context-based Representations for Classification Problems in Health Informatics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarvnaz</namePart>
<namePart type="family">Karimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ross</namePart>
<namePart type="family">Sparks</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cecile</namePart>
<namePart type="family">Paris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">Raina</namePart>
<namePart type="family">MacIntyre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th BioNLP Workshop and Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Distributed representations of text can be used as features when training a statistical classifier. These representations may be created as a composition of word vectors or as context-based sentence vectors. We compare the two kinds of representations (word versus context) for three classification problems: influenza infection classification, drug usage classification and personal health mention classification. For statistical classifiers trained for each of these problems, context-based representations based on ELMo, Universal Sentence Encoder, Neural-Net Language Model and FLAIR are better than Word2Vec, GloVe and the two adapted using the MESH ontology. There is an improvement of 2-4% in the accuracy when these context-based representations are used instead of word-based representations.</abstract>
<identifier type="citekey">joshi-etal-2019-comparison</identifier>
<identifier type="doi">10.18653/v1/W19-5015</identifier>
<location>
<url>https://aclanthology.org/W19-5015</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>135</start>
<end>141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparison of Word-based and Context-based Representations for Classification Problems in Health Informatics
%A Joshi, Aditya
%A Karimi, Sarvnaz
%A Sparks, Ross
%A Paris, Cecile
%A MacIntyre, C. Raina
%Y Demner-Fushman, Dina
%Y Cohen, Kevin Bretonnel
%Y Ananiadou, Sophia
%Y Tsujii, Junichi
%S Proceedings of the 18th BioNLP Workshop and Shared Task
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F joshi-etal-2019-comparison
%X Distributed representations of text can be used as features when training a statistical classifier. These representations may be created as a composition of word vectors or as context-based sentence vectors. We compare the two kinds of representations (word versus context) for three classification problems: influenza infection classification, drug usage classification and personal health mention classification. For statistical classifiers trained for each of these problems, context-based representations based on ELMo, Universal Sentence Encoder, Neural-Net Language Model and FLAIR are better than Word2Vec, GloVe and the two adapted using the MESH ontology. There is an improvement of 2-4% in the accuracy when these context-based representations are used instead of word-based representations.
%R 10.18653/v1/W19-5015
%U https://aclanthology.org/W19-5015
%U https://doi.org/10.18653/v1/W19-5015
%P 135-141
Markdown (Informal)
[A Comparison of Word-based and Context-based Representations for Classification Problems in Health Informatics](https://aclanthology.org/W19-5015) (Joshi et al., BioNLP 2019)
ACL