@inproceedings{henry-etal-2017-evaluating,
title = "Evaluating Feature Extraction Methods for Knowledge-based Biomedical Word Sense Disambiguation",
author = "Henry, Sam and
Cuffy, Clint and
McInnes, Bridget",
editor = "Cohen, Kevin Bretonnel and
Demner-Fushman, Dina and
Ananiadou, Sophia and
Tsujii, Junichi",
booktitle = "{B}io{NLP} 2017",
month = aug,
year = "2017",
address = "Vancouver, Canada,",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2334",
doi = "10.18653/v1/W17-2334",
pages = "272--281",
abstract = "In this paper, we present an analysis of feature extraction methods via dimensionality reduction for the task of biomedical Word Sense Disambiguation (WSD). We modify the vector representations in the 2-MRD WSD algorithm, and evaluate four dimensionality reduction methods: Word Embeddings using Continuous Bag of Words and Skip Gram, Singular Value Decomposition (SVD), and Principal Component Analysis (PCA). We also evaluate the effects of vector size on the performance of each of these methods. Results are evaluated on five standard evaluation datasets (Abbrev.100, Abbrev.200, Abbrev.300, NLM-WSD, and MSH-WSD). We find that vector sizes of 100 are sufficient for all techniques except SVD, for which a vector size of 1500 is referred. We also show that SVD performs on par with Word Embeddings for all but one dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="henry-etal-2017-evaluating">
<titleInfo>
<title>Evaluating Feature Extraction Methods for Knowledge-based Biomedical Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sam</namePart>
<namePart type="family">Henry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clint</namePart>
<namePart type="family">Cuffy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bridget</namePart>
<namePart type="family">McInnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>BioNLP 2017</title>
</titleInfo>
<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">Dina</namePart>
<namePart type="family">Demner-Fushman</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">Vancouver, Canada,</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present an analysis of feature extraction methods via dimensionality reduction for the task of biomedical Word Sense Disambiguation (WSD). We modify the vector representations in the 2-MRD WSD algorithm, and evaluate four dimensionality reduction methods: Word Embeddings using Continuous Bag of Words and Skip Gram, Singular Value Decomposition (SVD), and Principal Component Analysis (PCA). We also evaluate the effects of vector size on the performance of each of these methods. Results are evaluated on five standard evaluation datasets (Abbrev.100, Abbrev.200, Abbrev.300, NLM-WSD, and MSH-WSD). We find that vector sizes of 100 are sufficient for all techniques except SVD, for which a vector size of 1500 is referred. We also show that SVD performs on par with Word Embeddings for all but one dataset.</abstract>
<identifier type="citekey">henry-etal-2017-evaluating</identifier>
<identifier type="doi">10.18653/v1/W17-2334</identifier>
<location>
<url>https://aclanthology.org/W17-2334</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>272</start>
<end>281</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Feature Extraction Methods for Knowledge-based Biomedical Word Sense Disambiguation
%A Henry, Sam
%A Cuffy, Clint
%A McInnes, Bridget
%Y Cohen, Kevin Bretonnel
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Tsujii, Junichi
%S BioNLP 2017
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada,
%F henry-etal-2017-evaluating
%X In this paper, we present an analysis of feature extraction methods via dimensionality reduction for the task of biomedical Word Sense Disambiguation (WSD). We modify the vector representations in the 2-MRD WSD algorithm, and evaluate four dimensionality reduction methods: Word Embeddings using Continuous Bag of Words and Skip Gram, Singular Value Decomposition (SVD), and Principal Component Analysis (PCA). We also evaluate the effects of vector size on the performance of each of these methods. Results are evaluated on five standard evaluation datasets (Abbrev.100, Abbrev.200, Abbrev.300, NLM-WSD, and MSH-WSD). We find that vector sizes of 100 are sufficient for all techniques except SVD, for which a vector size of 1500 is referred. We also show that SVD performs on par with Word Embeddings for all but one dataset.
%R 10.18653/v1/W17-2334
%U https://aclanthology.org/W17-2334
%U https://doi.org/10.18653/v1/W17-2334
%P 272-281
Markdown (Informal)
[Evaluating Feature Extraction Methods for Knowledge-based Biomedical Word Sense Disambiguation](https://aclanthology.org/W17-2334) (Henry et al., BioNLP 2017)
ACL