@inproceedings{eisele-chen-2010-multiun,
title = "{M}ulti{UN}: A Multilingual Corpus from United Nation Documents",
author = "Eisele, Andreas and
Chen, Yu",
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/686_Paper.pdf",
abstract = "This paper describes the acquisition, preparation and properties of a corpus extracted from the official documents of the United Nations (UN). This corpus is available in all 6 official languages of the UN, consisting of around 300 million words per language. We describe the methods we used for crawling, document formatting, and sentence alignment. This corpus also includes a common test set for machine translation. We present the results of a French-Chinese machine translation experiment performed on this corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eisele-chen-2010-multiun">
<titleInfo>
<title>MultiUN: A Multilingual Corpus from United Nation Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Eisele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Chen</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 paper describes the acquisition, preparation and properties of a corpus extracted from the official documents of the United Nations (UN). This corpus is available in all 6 official languages of the UN, consisting of around 300 million words per language. We describe the methods we used for crawling, document formatting, and sentence alignment. This corpus also includes a common test set for machine translation. We present the results of a French-Chinese machine translation experiment performed on this corpus.</abstract>
<identifier type="citekey">eisele-chen-2010-multiun</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/686_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiUN: A Multilingual Corpus from United Nation Documents
%A Eisele, Andreas
%A Chen, Yu
%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 eisele-chen-2010-multiun
%X This paper describes the acquisition, preparation and properties of a corpus extracted from the official documents of the United Nations (UN). This corpus is available in all 6 official languages of the UN, consisting of around 300 million words per language. We describe the methods we used for crawling, document formatting, and sentence alignment. This corpus also includes a common test set for machine translation. We present the results of a French-Chinese machine translation experiment performed on this corpus.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/686_Paper.pdf
Markdown (Informal)
[MultiUN: A Multilingual Corpus from United Nation Documents](http://www.lrec-conf.org/proceedings/lrec2010/pdf/686_Paper.pdf) (Eisele & Chen, LREC 2010)
ACL