@inproceedings{apidianaki-2008-translation,
title = "Translation-oriented Word Sense Induction Based on Parallel Corpora",
author = "Apidianaki, Marianna",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/822_paper.pdf",
abstract = "Word Sense Disambiguation (WSD) is an intermediate task that serves as a means to an end defined by the application in which it is to be used. However, different applications have varying disambiguation needs which should have an impact on the choice of the method and of the sense inventory used. The tendency towards application-oriented WSD becomes more and more evident, mostly because of the inadequacy of predefined sense inventories and the inefficacy of application-independent methods in accomplishing specific tasks. In this article, we present a data-driven method of sense induction, which combines contextual and translation information coming from a bilingual parallel training corpus. It consists of an unsupervised method that clusters semantically similar translation equivalents of source language (SL) polysemous words. The created clusters are projected on the SL words revealing their sense distinctions. Clustered equivalents describing a sense of a polysemous word can be considered as more or less commutable translations for an instance of the word carrying this sense. The resulting sense clusters can thus be used for WSD and sense annotation, as well as for lexical selection in translation applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="apidianaki-2008-translation">
<titleInfo>
<title>Translation-oriented Word Sense Induction Based on Parallel Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word Sense Disambiguation (WSD) is an intermediate task that serves as a means to an end defined by the application in which it is to be used. However, different applications have varying disambiguation needs which should have an impact on the choice of the method and of the sense inventory used. The tendency towards application-oriented WSD becomes more and more evident, mostly because of the inadequacy of predefined sense inventories and the inefficacy of application-independent methods in accomplishing specific tasks. In this article, we present a data-driven method of sense induction, which combines contextual and translation information coming from a bilingual parallel training corpus. It consists of an unsupervised method that clusters semantically similar translation equivalents of source language (SL) polysemous words. The created clusters are projected on the SL words revealing their sense distinctions. Clustered equivalents describing a sense of a polysemous word can be considered as more or less commutable translations for an instance of the word carrying this sense. The resulting sense clusters can thus be used for WSD and sense annotation, as well as for lexical selection in translation applications.</abstract>
<identifier type="citekey">apidianaki-2008-translation</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/822_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translation-oriented Word Sense Induction Based on Parallel Corpora
%A Apidianaki, Marianna
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F apidianaki-2008-translation
%X Word Sense Disambiguation (WSD) is an intermediate task that serves as a means to an end defined by the application in which it is to be used. However, different applications have varying disambiguation needs which should have an impact on the choice of the method and of the sense inventory used. The tendency towards application-oriented WSD becomes more and more evident, mostly because of the inadequacy of predefined sense inventories and the inefficacy of application-independent methods in accomplishing specific tasks. In this article, we present a data-driven method of sense induction, which combines contextual and translation information coming from a bilingual parallel training corpus. It consists of an unsupervised method that clusters semantically similar translation equivalents of source language (SL) polysemous words. The created clusters are projected on the SL words revealing their sense distinctions. Clustered equivalents describing a sense of a polysemous word can be considered as more or less commutable translations for an instance of the word carrying this sense. The resulting sense clusters can thus be used for WSD and sense annotation, as well as for lexical selection in translation applications.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/822_paper.pdf
Markdown (Informal)
[Translation-oriented Word Sense Induction Based on Parallel Corpora](http://www.lrec-conf.org/proceedings/lrec2008/pdf/822_paper.pdf) (Apidianaki, LREC 2008)
ACL