@inproceedings{lefever-etal-2012-discovering,
title = "Discovering Missing {W}ikipedia Inter-language Links by means of Cross-lingual Word Sense Disambiguation",
author = "Lefever, Els and
Hoste, V{\'e}ronique and
De Cock, Martine",
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/508_Paper.pdf",
pages = "841--846",
abstract = "Wikipedia pages typically contain inter-language links to the corresponding pages in other languages. These links, however, are often incomplete. This paper describes a set of experiments in which the viability of discovering such missing inter-language links for ambiguous nouns by means of a cross-lingual Word Sense Disambiguation approach is investigated. The input for the inter-language link detection system is a set of Dutch pages for a given ambiguous noun and the output of the system is a set of links to the corresponding pages in three target languages (viz. French, Spanish and Italian). The experimental results show that although it is a very challenging task, the system succeeds to detect missing inter-language links between Wikipedia documents for a manually labeled test set. The final goal of the system is to provide a human editor with a list of possible missing links that should be manually verified.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lefever-etal-2012-discovering">
<titleInfo>
<title>Discovering Missing Wikipedia Inter-language Links by means of Cross-lingual Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Véronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martine</namePart>
<namePart type="family">De Cock</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>Wikipedia pages typically contain inter-language links to the corresponding pages in other languages. These links, however, are often incomplete. This paper describes a set of experiments in which the viability of discovering such missing inter-language links for ambiguous nouns by means of a cross-lingual Word Sense Disambiguation approach is investigated. The input for the inter-language link detection system is a set of Dutch pages for a given ambiguous noun and the output of the system is a set of links to the corresponding pages in three target languages (viz. French, Spanish and Italian). The experimental results show that although it is a very challenging task, the system succeeds to detect missing inter-language links between Wikipedia documents for a manually labeled test set. The final goal of the system is to provide a human editor with a list of possible missing links that should be manually verified.</abstract>
<identifier type="citekey">lefever-etal-2012-discovering</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/508_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>841</start>
<end>846</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discovering Missing Wikipedia Inter-language Links by means of Cross-lingual Word Sense Disambiguation
%A Lefever, Els
%A Hoste, Véronique
%A De Cock, Martine
%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 lefever-etal-2012-discovering
%X Wikipedia pages typically contain inter-language links to the corresponding pages in other languages. These links, however, are often incomplete. This paper describes a set of experiments in which the viability of discovering such missing inter-language links for ambiguous nouns by means of a cross-lingual Word Sense Disambiguation approach is investigated. The input for the inter-language link detection system is a set of Dutch pages for a given ambiguous noun and the output of the system is a set of links to the corresponding pages in three target languages (viz. French, Spanish and Italian). The experimental results show that although it is a very challenging task, the system succeeds to detect missing inter-language links between Wikipedia documents for a manually labeled test set. The final goal of the system is to provide a human editor with a list of possible missing links that should be manually verified.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/508_Paper.pdf
%P 841-846
Markdown (Informal)
[Discovering Missing Wikipedia Inter-language Links by means of Cross-lingual Word Sense Disambiguation](http://www.lrec-conf.org/proceedings/lrec2012/pdf/508_Paper.pdf) (Lefever et al., LREC 2012)
ACL