@inproceedings{reese-etal-2010-wikicorpus,
title = "{W}ikicorpus: A Word-Sense Disambiguated Multilingual {W}ikipedia Corpus",
author = "Reese, Samuel and
Boleda, Gemma and
Cuadros, Montse and
Padr{\'o}, Llu{\'\i}s and
Rigau, German",
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/222_Paper.pdf",
abstract = "This article presents a new freely available trilingual corpus (Catalan, Spanish, English) that contains large portions of the Wikipedia and has been automatically enriched with linguistic information. To our knowledge, this is the largest such corpus that is freely available to the community: In its present version, it contains over 750 million words. The corpora have been annotated with lemma and part of speech information using the open source library FreeLing. Also, they have been sense annotated with the state of the art Word Sense Disambiguation algorithm UKB. As UKB assigns WordNet senses, and WordNet has been aligned across languages via the InterLingual Index, this sort of annotation opens the way to massive explorations in lexical semantics that were not possible before. We present a first attempt at creating a trilingual lexical resource from the sense-tagged Wikipedia corpora, namely, WikiNet. Moreover, we present two by-products of the project that are of use for the NLP community: An open source Java-based parser for Wikipedia pages developed for the construction of the corpus, and the integration of the WSD algorithm UKB in FreeLing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reese-etal-2010-wikicorpus">
<titleInfo>
<title>Wikicorpus: A Word-Sense Disambiguated Multilingual Wikipedia Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Reese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gemma</namePart>
<namePart type="family">Boleda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Montse</namePart>
<namePart type="family">Cuadros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Padró</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</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>This article presents a new freely available trilingual corpus (Catalan, Spanish, English) that contains large portions of the Wikipedia and has been automatically enriched with linguistic information. To our knowledge, this is the largest such corpus that is freely available to the community: In its present version, it contains over 750 million words. The corpora have been annotated with lemma and part of speech information using the open source library FreeLing. Also, they have been sense annotated with the state of the art Word Sense Disambiguation algorithm UKB. As UKB assigns WordNet senses, and WordNet has been aligned across languages via the InterLingual Index, this sort of annotation opens the way to massive explorations in lexical semantics that were not possible before. We present a first attempt at creating a trilingual lexical resource from the sense-tagged Wikipedia corpora, namely, WikiNet. Moreover, we present two by-products of the project that are of use for the NLP community: An open source Java-based parser for Wikipedia pages developed for the construction of the corpus, and the integration of the WSD algorithm UKB in FreeLing.</abstract>
<identifier type="citekey">reese-etal-2010-wikicorpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/222_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wikicorpus: A Word-Sense Disambiguated Multilingual Wikipedia Corpus
%A Reese, Samuel
%A Boleda, Gemma
%A Cuadros, Montse
%A Padró, Lluís
%A Rigau, German
%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 reese-etal-2010-wikicorpus
%X This article presents a new freely available trilingual corpus (Catalan, Spanish, English) that contains large portions of the Wikipedia and has been automatically enriched with linguistic information. To our knowledge, this is the largest such corpus that is freely available to the community: In its present version, it contains over 750 million words. The corpora have been annotated with lemma and part of speech information using the open source library FreeLing. Also, they have been sense annotated with the state of the art Word Sense Disambiguation algorithm UKB. As UKB assigns WordNet senses, and WordNet has been aligned across languages via the InterLingual Index, this sort of annotation opens the way to massive explorations in lexical semantics that were not possible before. We present a first attempt at creating a trilingual lexical resource from the sense-tagged Wikipedia corpora, namely, WikiNet. Moreover, we present two by-products of the project that are of use for the NLP community: An open source Java-based parser for Wikipedia pages developed for the construction of the corpus, and the integration of the WSD algorithm UKB in FreeLing.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/222_Paper.pdf
Markdown (Informal)
[Wikicorpus: A Word-Sense Disambiguated Multilingual Wikipedia Corpus](http://www.lrec-conf.org/proceedings/lrec2010/pdf/222_Paper.pdf) (Reese et al., LREC 2010)
ACL