@inproceedings{fiser-etal-2012-addressing,
title = "Addressing polysemy in bilingual lexicon extraction from comparable corpora",
author = "Fi{\v{s}}er, Darja and
Ljube{\v{s}}i{\'c}, Nikola and
Kubelka, Ozren",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/601_Paper.pdf",
pages = "3031--3035",
abstract = "This paper presents an approach to extract translation equivalents from comparable corpora for polysemous nouns. As opposed to the standard approaches that build a single context vector for all occurrences of a given headword, we first disambiguate the headword with third-party sense taggers and then build a separate context vector for each sense of the headword. Since state-of-the-art word sense disambiguation tools are still far from perfect, we also tried to improve the results by combining the sense assignments provided by two different sense taggers. Evaluation of the results shows that we outperform the baseline (0.473) in all the settings we experimented with, even when using only one sense tagger, and that the best-performing results are indeed obtained by taking into account the intersection of both sense taggers (0.720).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fiser-etal-2012-addressing">
<titleInfo>
<title>Addressing polysemy in bilingual lexicon extraction from comparable corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ozren</namePart>
<namePart type="family">Kubelka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents an approach to extract translation equivalents from comparable corpora for polysemous nouns. As opposed to the standard approaches that build a single context vector for all occurrences of a given headword, we first disambiguate the headword with third-party sense taggers and then build a separate context vector for each sense of the headword. Since state-of-the-art word sense disambiguation tools are still far from perfect, we also tried to improve the results by combining the sense assignments provided by two different sense taggers. Evaluation of the results shows that we outperform the baseline (0.473) in all the settings we experimented with, even when using only one sense tagger, and that the best-performing results are indeed obtained by taking into account the intersection of both sense taggers (0.720).</abstract>
<identifier type="citekey">fiser-etal-2012-addressing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/601_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3031</start>
<end>3035</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Addressing polysemy in bilingual lexicon extraction from comparable corpora
%A Fišer, Darja
%A Ljubešić, Nikola
%A Kubelka, Ozren
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F fiser-etal-2012-addressing
%X This paper presents an approach to extract translation equivalents from comparable corpora for polysemous nouns. As opposed to the standard approaches that build a single context vector for all occurrences of a given headword, we first disambiguate the headword with third-party sense taggers and then build a separate context vector for each sense of the headword. Since state-of-the-art word sense disambiguation tools are still far from perfect, we also tried to improve the results by combining the sense assignments provided by two different sense taggers. Evaluation of the results shows that we outperform the baseline (0.473) in all the settings we experimented with, even when using only one sense tagger, and that the best-performing results are indeed obtained by taking into account the intersection of both sense taggers (0.720).
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/601_Paper.pdf
%P 3031-3035
Markdown (Informal)
[Addressing polysemy in bilingual lexicon extraction from comparable corpora](http://www.lrec-conf.org/proceedings/lrec2012/pdf/601_Paper.pdf) (Fišer et al., LREC 2012)
ACL