@inproceedings{majlis-zabokrtsky-2012-language,
title = "Language Richness of the Web",
author = "Majli{\v{s}}, Martin and
{\v{Z}}abokrtsk{\'y}, Zden{\v{e}}k",
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/267_Paper.pdf",
pages = "2927--2934",
abstract = "We have built a corpus containing texts in 106 languages from texts available on the Internet and on Wikipedia. The W2C Web Corpus contains 54.7{\textasciitilde}GB of text and the W2C Wiki Corpus contains 8.5{\textasciitilde}GB of text. The W2C Web Corpus contains more than 100{\textasciitilde}MB of text available for 75 languages. At least 10{\textasciitilde}MB of text is available for 100 languages. These corpora are a unique data source for linguists, since they outclass all published works both in the size of the material collected and the number of languages covered. This language data resource can be of use particularly to researchers specialized in multilingual technologies development. We also developed software that greatly simplifies the creation of a new text corpus for a given language, using text materials freely available on the Internet. Special attention was given to components for filtering and de-duplication that allow to keep the material quality very high.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="majlis-zabokrtsky-2012-language">
<titleInfo>
<title>Language Richness of the Web</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Majliš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zdeněk</namePart>
<namePart type="family">Žabokrtský</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>We have built a corpus containing texts in 106 languages from texts available on the Internet and on Wikipedia. The W2C Web Corpus contains 54.7~GB of text and the W2C Wiki Corpus contains 8.5~GB of text. The W2C Web Corpus contains more than 100~MB of text available for 75 languages. At least 10~MB of text is available for 100 languages. These corpora are a unique data source for linguists, since they outclass all published works both in the size of the material collected and the number of languages covered. This language data resource can be of use particularly to researchers specialized in multilingual technologies development. We also developed software that greatly simplifies the creation of a new text corpus for a given language, using text materials freely available on the Internet. Special attention was given to components for filtering and de-duplication that allow to keep the material quality very high.</abstract>
<identifier type="citekey">majlis-zabokrtsky-2012-language</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/267_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2927</start>
<end>2934</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Richness of the Web
%A Majliš, Martin
%A Žabokrtský, Zdeněk
%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 majlis-zabokrtsky-2012-language
%X We have built a corpus containing texts in 106 languages from texts available on the Internet and on Wikipedia. The W2C Web Corpus contains 54.7~GB of text and the W2C Wiki Corpus contains 8.5~GB of text. The W2C Web Corpus contains more than 100~MB of text available for 75 languages. At least 10~MB of text is available for 100 languages. These corpora are a unique data source for linguists, since they outclass all published works both in the size of the material collected and the number of languages covered. This language data resource can be of use particularly to researchers specialized in multilingual technologies development. We also developed software that greatly simplifies the creation of a new text corpus for a given language, using text materials freely available on the Internet. Special attention was given to components for filtering and de-duplication that allow to keep the material quality very high.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/267_Paper.pdf
%P 2927-2934
Markdown (Informal)
[Language Richness of the Web](http://www.lrec-conf.org/proceedings/lrec2012/pdf/267_Paper.pdf) (Majliš & Žabokrtský, LREC 2012)
ACL
- Martin Majliš and Zdeněk Žabokrtský. 2012. Language Richness of the Web. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2927–2934, Istanbul, Turkey. European Language Resources Association (ELRA).