@inproceedings{yadav-etal-2017-entity,
title = "Entity Extraction in Biomedical Corpora: An Approach to Evaluate Word Embedding Features with {PSO} based Feature Selection",
author = "Yadav, Shweta and
Ekbal, Asif and
Saha, Sriparna and
Bhattacharyya, Pushpak",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-1109",
pages = "1159--1170",
abstract = "Text mining has drawn significant attention in recent past due to the rapid growth in biomedical and clinical records. Entity extraction is one of the fundamental components for biomedical text mining. In this paper, we propose a novel approach of feature selection for entity extraction that exploits the concept of deep learning and Particle Swarm Optimization (PSO). The system utilizes word embedding features along with several other features extracted by studying the properties of the datasets. We obtain an interesting observation that compact word embedding features as determined by PSO are more effective compared to the entire word embedding feature set for entity extraction. The proposed system is evaluated on three benchmark biomedical datasets such as GENIA, GENETAG, and AiMed. The effectiveness of the proposed approach is evident with significant performance gains over the baseline models as well as the other existing systems. We observe improvements of 7.86{\%}, 5.27{\%} and 7.25{\%} F-measure points over the baseline models for GENIA, GENETAG, and AiMed dataset respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-etal-2017-entity">
<titleInfo>
<title>Entity Extraction in Biomedical Corpora: An Approach to Evaluate Word Embedding Features with PSO based Feature Selection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shweta</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text mining has drawn significant attention in recent past due to the rapid growth in biomedical and clinical records. Entity extraction is one of the fundamental components for biomedical text mining. In this paper, we propose a novel approach of feature selection for entity extraction that exploits the concept of deep learning and Particle Swarm Optimization (PSO). The system utilizes word embedding features along with several other features extracted by studying the properties of the datasets. We obtain an interesting observation that compact word embedding features as determined by PSO are more effective compared to the entire word embedding feature set for entity extraction. The proposed system is evaluated on three benchmark biomedical datasets such as GENIA, GENETAG, and AiMed. The effectiveness of the proposed approach is evident with significant performance gains over the baseline models as well as the other existing systems. We observe improvements of 7.86%, 5.27% and 7.25% F-measure points over the baseline models for GENIA, GENETAG, and AiMed dataset respectively.</abstract>
<identifier type="citekey">yadav-etal-2017-entity</identifier>
<location>
<url>https://aclanthology.org/E17-1109</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>1159</start>
<end>1170</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity Extraction in Biomedical Corpora: An Approach to Evaluate Word Embedding Features with PSO based Feature Selection
%A Yadav, Shweta
%A Ekbal, Asif
%A Saha, Sriparna
%A Bhattacharyya, Pushpak
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F yadav-etal-2017-entity
%X Text mining has drawn significant attention in recent past due to the rapid growth in biomedical and clinical records. Entity extraction is one of the fundamental components for biomedical text mining. In this paper, we propose a novel approach of feature selection for entity extraction that exploits the concept of deep learning and Particle Swarm Optimization (PSO). The system utilizes word embedding features along with several other features extracted by studying the properties of the datasets. We obtain an interesting observation that compact word embedding features as determined by PSO are more effective compared to the entire word embedding feature set for entity extraction. The proposed system is evaluated on three benchmark biomedical datasets such as GENIA, GENETAG, and AiMed. The effectiveness of the proposed approach is evident with significant performance gains over the baseline models as well as the other existing systems. We observe improvements of 7.86%, 5.27% and 7.25% F-measure points over the baseline models for GENIA, GENETAG, and AiMed dataset respectively.
%U https://aclanthology.org/E17-1109
%P 1159-1170
Markdown (Informal)
[Entity Extraction in Biomedical Corpora: An Approach to Evaluate Word Embedding Features with PSO based Feature Selection](https://aclanthology.org/E17-1109) (Yadav et al., EACL 2017)
ACL