@inproceedings{lardilleux-etal-2010-bilingual,
title = "Bilingual Lexicon Induction: Effortless Evaluation of Word Alignment Tools and Production of Resources for Improbable Language Pairs",
author = "Lardilleux, Adrien and
Gosme, Julien and
Lepage, Yves",
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/293_Paper.pdf",
abstract = "In this paper, we present a simple protocol to evaluate word aligners on bilingual lexicon induction tasks from parallel corpora. Rather than resorting to gold standards, it relies on a comparison of the outputs of word aligners against a reference bilingual lexicon. The quality of this reference bilingual lexicon does not need to be particularly high, because evaluation quality is ensured by systematically filtering this reference lexicon with the parallel corpus the word aligners are trained on. We perform a comparison of three freely available word aligners on numerous language pairs from the Bible parallel corpus (Resnik et al., 1999): MGIZA++ (Gao and Vogel, 2008), BerkeleyAligner (Liang et al., 2006), and Anymalign (Lardilleux and Lepage, 2009). We then select the most appropriate one to produce bilingual lexicons for all language pairs of this corpus. These involve Cebuano, Chinese, Danish, English, Finnish, French, Greek, Indonesian, Latin, Spanish, Swedish, and Vietnamese. The 66 resulting lexicons are made freely available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lardilleux-etal-2010-bilingual">
<titleInfo>
<title>Bilingual Lexicon Induction: Effortless Evaluation of Word Alignment Tools and Production of Resources for Improbable Language Pairs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adrien</namePart>
<namePart type="family">Lardilleux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Gosme</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Lepage</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>In this paper, we present a simple protocol to evaluate word aligners on bilingual lexicon induction tasks from parallel corpora. Rather than resorting to gold standards, it relies on a comparison of the outputs of word aligners against a reference bilingual lexicon. The quality of this reference bilingual lexicon does not need to be particularly high, because evaluation quality is ensured by systematically filtering this reference lexicon with the parallel corpus the word aligners are trained on. We perform a comparison of three freely available word aligners on numerous language pairs from the Bible parallel corpus (Resnik et al., 1999): MGIZA++ (Gao and Vogel, 2008), BerkeleyAligner (Liang et al., 2006), and Anymalign (Lardilleux and Lepage, 2009). We then select the most appropriate one to produce bilingual lexicons for all language pairs of this corpus. These involve Cebuano, Chinese, Danish, English, Finnish, French, Greek, Indonesian, Latin, Spanish, Swedish, and Vietnamese. The 66 resulting lexicons are made freely available.</abstract>
<identifier type="citekey">lardilleux-etal-2010-bilingual</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/293_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Lexicon Induction: Effortless Evaluation of Word Alignment Tools and Production of Resources for Improbable Language Pairs
%A Lardilleux, Adrien
%A Gosme, Julien
%A Lepage, Yves
%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 lardilleux-etal-2010-bilingual
%X In this paper, we present a simple protocol to evaluate word aligners on bilingual lexicon induction tasks from parallel corpora. Rather than resorting to gold standards, it relies on a comparison of the outputs of word aligners against a reference bilingual lexicon. The quality of this reference bilingual lexicon does not need to be particularly high, because evaluation quality is ensured by systematically filtering this reference lexicon with the parallel corpus the word aligners are trained on. We perform a comparison of three freely available word aligners on numerous language pairs from the Bible parallel corpus (Resnik et al., 1999): MGIZA++ (Gao and Vogel, 2008), BerkeleyAligner (Liang et al., 2006), and Anymalign (Lardilleux and Lepage, 2009). We then select the most appropriate one to produce bilingual lexicons for all language pairs of this corpus. These involve Cebuano, Chinese, Danish, English, Finnish, French, Greek, Indonesian, Latin, Spanish, Swedish, and Vietnamese. The 66 resulting lexicons are made freely available.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/293_Paper.pdf
Markdown (Informal)
[Bilingual Lexicon Induction: Effortless Evaluation of Word Alignment Tools and Production of Resources for Improbable Language Pairs](http://www.lrec-conf.org/proceedings/lrec2010/pdf/293_Paper.pdf) (Lardilleux et al., LREC 2010)
ACL