@inproceedings{schwarz-etal-2010-identification,
title = "Identification of Rare {\&} Novel Senses Using Translations in a Parallel Corpus",
author = {Schwarz, Richard and
Sch{\"u}tze, Hinrich and
Martin, Fabienne and
Stein, Achim},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/411_Paper.pdf",
abstract = "The identification of rare and novel senses is a challenge in lexicography. In this paper, we present a new method for finding such senses using a word aligned multilingual parallel corpus. We use the Europarl corpus and therein concentrate on French verbs. We represent each occurrence of a French verb as a high dimensional term vector. The dimensions of such a vector are the possible translations of the verb according to the underlying word alignment. The dimensions are weighted by a weighting scheme to adjust to the significance of any particular translation. After collecting these vectors we apply forms of the K-means algorithm on the resulting vector space to produce clusters of distinct senses, so that standard uses produce large homogeneous clusters while rare and novel uses appear in small or heterogeneous clusters. We show in a qualitative and quantitative evaluation that the method can successfully find rare and novel senses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schwarz-etal-2010-identification">
<titleInfo>
<title>Identification of Rare & Novel Senses Using Translations in a Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Schwarz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schütze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabienne</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Achim</namePart>
<namePart type="family">Stein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The identification of rare and novel senses is a challenge in lexicography. In this paper, we present a new method for finding such senses using a word aligned multilingual parallel corpus. We use the Europarl corpus and therein concentrate on French verbs. We represent each occurrence of a French verb as a high dimensional term vector. The dimensions of such a vector are the possible translations of the verb according to the underlying word alignment. The dimensions are weighted by a weighting scheme to adjust to the significance of any particular translation. After collecting these vectors we apply forms of the K-means algorithm on the resulting vector space to produce clusters of distinct senses, so that standard uses produce large homogeneous clusters while rare and novel uses appear in small or heterogeneous clusters. We show in a qualitative and quantitative evaluation that the method can successfully find rare and novel senses.</abstract>
<identifier type="citekey">schwarz-etal-2010-identification</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/411_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identification of Rare & Novel Senses Using Translations in a Parallel Corpus
%A Schwarz, Richard
%A Schütze, Hinrich
%A Martin, Fabienne
%A Stein, Achim
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F schwarz-etal-2010-identification
%X The identification of rare and novel senses is a challenge in lexicography. In this paper, we present a new method for finding such senses using a word aligned multilingual parallel corpus. We use the Europarl corpus and therein concentrate on French verbs. We represent each occurrence of a French verb as a high dimensional term vector. The dimensions of such a vector are the possible translations of the verb according to the underlying word alignment. The dimensions are weighted by a weighting scheme to adjust to the significance of any particular translation. After collecting these vectors we apply forms of the K-means algorithm on the resulting vector space to produce clusters of distinct senses, so that standard uses produce large homogeneous clusters while rare and novel uses appear in small or heterogeneous clusters. We show in a qualitative and quantitative evaluation that the method can successfully find rare and novel senses.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/411_Paper.pdf
Markdown (Informal)
[Identification of Rare & Novel Senses Using Translations in a Parallel Corpus](http://www.lrec-conf.org/proceedings/lrec2010/pdf/411_Paper.pdf) (Schwarz et al., LREC 2010)
ACL