@inproceedings{chatzimina-etal-2014-use,
title = "Use of unsupervised word classes for entity recognition: Application to the detection of disorders in clinical reports",
author = "Chatzimina, Maria Evangelia and
Grouin, Cyril and
Zweigenbaum, Pierre",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/389_Paper.pdf",
pages = "3264--3271",
abstract = "Unsupervised word classes induced from unannotated text corpora are increasingly used to help tasks addressed by supervised classification, such as standard named entity detection. This paper studies the contribution of unsupervised word classes to a medical entity detection task with two specific objectives: How do unsupervised word classes compare to available knowledge-based semantic classes? Does syntactic information help produce unsupervised word classes with better properties? We design and test two syntax-based methods to produce word classes: one applies the Brown clustering algorithm to syntactic dependencies, the other collects latent categories created by a PCFG-LA parser. When added to non-semantic features, knowledge-based semantic classes gain 7.28 points of F-measure. In the same context, basic unsupervised word classes gain 4.16pt, reaching 60{\%} of the contribution of knowledge-based semantic classes and outperforming Wikipedia, and adding PCFG-LA unsupervised word classes gain one more point at 5.11pt, reaching 70{\%}. Unsupervised word classes could therefore provide a useful semantic back-off in domains where no knowledge-based semantic classes are available. The combination of both knowledge-based and basic unsupervised classes gains 8.33pt. Therefore, unsupervised classes are still useful even when rich knowledge-based classes exist.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chatzimina-etal-2014-use">
<titleInfo>
<title>Use of unsupervised word classes for entity recognition: Application to the detection of disorders in clinical reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Evangelia</namePart>
<namePart type="family">Chatzimina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Grouin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unsupervised word classes induced from unannotated text corpora are increasingly used to help tasks addressed by supervised classification, such as standard named entity detection. This paper studies the contribution of unsupervised word classes to a medical entity detection task with two specific objectives: How do unsupervised word classes compare to available knowledge-based semantic classes? Does syntactic information help produce unsupervised word classes with better properties? We design and test two syntax-based methods to produce word classes: one applies the Brown clustering algorithm to syntactic dependencies, the other collects latent categories created by a PCFG-LA parser. When added to non-semantic features, knowledge-based semantic classes gain 7.28 points of F-measure. In the same context, basic unsupervised word classes gain 4.16pt, reaching 60% of the contribution of knowledge-based semantic classes and outperforming Wikipedia, and adding PCFG-LA unsupervised word classes gain one more point at 5.11pt, reaching 70%. Unsupervised word classes could therefore provide a useful semantic back-off in domains where no knowledge-based semantic classes are available. The combination of both knowledge-based and basic unsupervised classes gains 8.33pt. Therefore, unsupervised classes are still useful even when rich knowledge-based classes exist.</abstract>
<identifier type="citekey">chatzimina-etal-2014-use</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/389_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3264</start>
<end>3271</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Use of unsupervised word classes for entity recognition: Application to the detection of disorders in clinical reports
%A Chatzimina, Maria Evangelia
%A Grouin, Cyril
%A Zweigenbaum, Pierre
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F chatzimina-etal-2014-use
%X Unsupervised word classes induced from unannotated text corpora are increasingly used to help tasks addressed by supervised classification, such as standard named entity detection. This paper studies the contribution of unsupervised word classes to a medical entity detection task with two specific objectives: How do unsupervised word classes compare to available knowledge-based semantic classes? Does syntactic information help produce unsupervised word classes with better properties? We design and test two syntax-based methods to produce word classes: one applies the Brown clustering algorithm to syntactic dependencies, the other collects latent categories created by a PCFG-LA parser. When added to non-semantic features, knowledge-based semantic classes gain 7.28 points of F-measure. In the same context, basic unsupervised word classes gain 4.16pt, reaching 60% of the contribution of knowledge-based semantic classes and outperforming Wikipedia, and adding PCFG-LA unsupervised word classes gain one more point at 5.11pt, reaching 70%. Unsupervised word classes could therefore provide a useful semantic back-off in domains where no knowledge-based semantic classes are available. The combination of both knowledge-based and basic unsupervised classes gains 8.33pt. Therefore, unsupervised classes are still useful even when rich knowledge-based classes exist.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/389_Paper.pdf
%P 3264-3271
Markdown (Informal)
[Use of unsupervised word classes for entity recognition: Application to the detection of disorders in clinical reports](http://www.lrec-conf.org/proceedings/lrec2014/pdf/389_Paper.pdf) (Chatzimina et al., LREC 2014)
ACL