@inproceedings{limsopatham-collier-2016-learning,
title = "Learning Orthographic Features in Bi-directional {LSTM} for Biomedical Named Entity Recognition",
author = "Limsopatham, Nut and
Collier, Nigel",
editor = "Ananiadou, Sophia and
Batista-Navarro, Riza and
Cohen, Kevin Bretonnel and
Demner-Fushman, Dina and
Thompson, Paul",
booktitle = "Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining ({B}io{T}xt{M}2016)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-5102",
pages = "10--19",
abstract = "End-to-end neural network models for named entity recognition (NER) have shown to achieve effective performances on general domain datasets (e.g. newswire), without requiring additional hand-crafted features. However, in biomedical domain, recent studies have shown that hand-engineered features (e.g. orthographic features) should be used to attain effective performance, due to the complexity of biomedical terminology (e.g. the use of acronyms and complex gene names). In this work, we propose a novel approach that allows a neural network model based on a long short-term memory (LSTM) to automatically learn orthographic features and incorporate them into a model for biomedical NER. Importantly, our bi-directional LSTM model learns and leverages orthographic features on an end-to-end basis. We evaluate our approach by comparing against existing neural network models for NER using three well-established biomedical datasets. Our experimental results show that the proposed approach consistently outperforms these strong baselines across all of the three datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="limsopatham-collier-2016-learning">
<titleInfo>
<title>Learning Orthographic Features in Bi-directional LSTM for Biomedical Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nut</namePart>
<namePart type="family">Limsopatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nigel</namePart>
<namePart type="family">Collier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016)</title>
</titleInfo>
<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">Riza</namePart>
<namePart type="family">Batista-Navarro</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">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>End-to-end neural network models for named entity recognition (NER) have shown to achieve effective performances on general domain datasets (e.g. newswire), without requiring additional hand-crafted features. However, in biomedical domain, recent studies have shown that hand-engineered features (e.g. orthographic features) should be used to attain effective performance, due to the complexity of biomedical terminology (e.g. the use of acronyms and complex gene names). In this work, we propose a novel approach that allows a neural network model based on a long short-term memory (LSTM) to automatically learn orthographic features and incorporate them into a model for biomedical NER. Importantly, our bi-directional LSTM model learns and leverages orthographic features on an end-to-end basis. We evaluate our approach by comparing against existing neural network models for NER using three well-established biomedical datasets. Our experimental results show that the proposed approach consistently outperforms these strong baselines across all of the three datasets.</abstract>
<identifier type="citekey">limsopatham-collier-2016-learning</identifier>
<location>
<url>https://aclanthology.org/W16-5102</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>10</start>
<end>19</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Orthographic Features in Bi-directional LSTM for Biomedical Named Entity Recognition
%A Limsopatham, Nut
%A Collier, Nigel
%Y Ananiadou, Sophia
%Y Batista-Navarro, Riza
%Y Cohen, Kevin Bretonnel
%Y Demner-Fushman, Dina
%Y Thompson, Paul
%S Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F limsopatham-collier-2016-learning
%X End-to-end neural network models for named entity recognition (NER) have shown to achieve effective performances on general domain datasets (e.g. newswire), without requiring additional hand-crafted features. However, in biomedical domain, recent studies have shown that hand-engineered features (e.g. orthographic features) should be used to attain effective performance, due to the complexity of biomedical terminology (e.g. the use of acronyms and complex gene names). In this work, we propose a novel approach that allows a neural network model based on a long short-term memory (LSTM) to automatically learn orthographic features and incorporate them into a model for biomedical NER. Importantly, our bi-directional LSTM model learns and leverages orthographic features on an end-to-end basis. We evaluate our approach by comparing against existing neural network models for NER using three well-established biomedical datasets. Our experimental results show that the proposed approach consistently outperforms these strong baselines across all of the three datasets.
%U https://aclanthology.org/W16-5102
%P 10-19
Markdown (Informal)
[Learning Orthographic Features in Bi-directional LSTM for Biomedical Named Entity Recognition](https://aclanthology.org/W16-5102) (Limsopatham & Collier, 2016)
ACL