@inproceedings{erjavec-2010-multext,
title = "{MULTEXT}-East Version 4: Multilingual Morphosyntactic Specifications, Lexicons and Corpora",
author = "Erjavec, Toma{\v{z}}",
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/138_Paper.pdf",
abstract = "The paper presents the fourth, ``Mondilex'' edition of the MULTEXT-East language resources, a multilingual dataset for language engineering research and development, focused on the morphosyntactic level of linguistic description. This standardised and linked set of resources covers a large number of mainly Central and Eastern European languages and includes the EAGLES-based morphosyntactic specifications; morphosyntactic lexica; and annotated parallel, comparable, and speech corpora. The fourth release of these resources introduces XML-encoded morphosyntactic specifications and adds six new languages, bringing the total to 16: to Bulgarian, Croatian, Czech, Estonian, English, Hungarian, Romanian, Serbian, Slovene, and the Resian dialect of Slovene it adds Macedonian, Persian, Polish, Russian, Slovak, and Ukrainian. This dataset, unique in terms of languages covered and the wealth of encoding, is extensively documented, and freely available for research purposes at \url{http://nl.ijs.si/ME/V4/}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="erjavec-2010-multext">
<titleInfo>
<title>MULTEXT-East Version 4: Multilingual Morphosyntactic Specifications, Lexicons and Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</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 paper presents the fourth, “Mondilex” edition of the MULTEXT-East language resources, a multilingual dataset for language engineering research and development, focused on the morphosyntactic level of linguistic description. This standardised and linked set of resources covers a large number of mainly Central and Eastern European languages and includes the EAGLES-based morphosyntactic specifications; morphosyntactic lexica; and annotated parallel, comparable, and speech corpora. The fourth release of these resources introduces XML-encoded morphosyntactic specifications and adds six new languages, bringing the total to 16: to Bulgarian, Croatian, Czech, Estonian, English, Hungarian, Romanian, Serbian, Slovene, and the Resian dialect of Slovene it adds Macedonian, Persian, Polish, Russian, Slovak, and Ukrainian. This dataset, unique in terms of languages covered and the wealth of encoding, is extensively documented, and freely available for research purposes at http://nl.ijs.si/ME/V4/.</abstract>
<identifier type="citekey">erjavec-2010-multext</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/138_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MULTEXT-East Version 4: Multilingual Morphosyntactic Specifications, Lexicons and Corpora
%A Erjavec, Tomaž
%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 erjavec-2010-multext
%X The paper presents the fourth, “Mondilex” edition of the MULTEXT-East language resources, a multilingual dataset for language engineering research and development, focused on the morphosyntactic level of linguistic description. This standardised and linked set of resources covers a large number of mainly Central and Eastern European languages and includes the EAGLES-based morphosyntactic specifications; morphosyntactic lexica; and annotated parallel, comparable, and speech corpora. The fourth release of these resources introduces XML-encoded morphosyntactic specifications and adds six new languages, bringing the total to 16: to Bulgarian, Croatian, Czech, Estonian, English, Hungarian, Romanian, Serbian, Slovene, and the Resian dialect of Slovene it adds Macedonian, Persian, Polish, Russian, Slovak, and Ukrainian. This dataset, unique in terms of languages covered and the wealth of encoding, is extensively documented, and freely available for research purposes at http://nl.ijs.si/ME/V4/.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/138_Paper.pdf
Markdown (Informal)
[MULTEXT-East Version 4: Multilingual Morphosyntactic Specifications, Lexicons and Corpora](http://www.lrec-conf.org/proceedings/lrec2010/pdf/138_Paper.pdf) (Erjavec, LREC 2010)
ACL