@inproceedings{chen-eisele-2012-multiun,
title = "{M}ulti{UN} v2: {UN} Documents with Multilingual Alignments",
author = "Chen, Yu and
Eisele, Andreas",
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/641_Paper.pdf",
pages = "2500--2504",
abstract = "MultiUN is a multilingual parallel corpus extracted from the official documents of the United Nations. It is available in the six official languages of the UN and a small portion of it is also available in German. This paper presents a major update on the first public version of the corpus released in 2010. This version 2 consists of over 513,091 documents, including more than 9{\%} of new documents retrieved from the United Nations official document system. We applied several modifications to the corpus preparation method. In this paper, we describe the methods we used for processing the UN documents and aligning the sentences. The most significant improvement compared to the previous release is the newly added multilingual sentence alignment information. The alignment information is encoded together with the text in XML instead of additional files. Our representation of the sentence alignment allows quick construction of aligned texts parallel in arbitrary number of languages, which is essential for building machine translation systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-eisele-2012-multiun">
<titleInfo>
<title>MultiUN v2: UN Documents with Multilingual Alignments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Eisele</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>MultiUN is a multilingual parallel corpus extracted from the official documents of the United Nations. It is available in the six official languages of the UN and a small portion of it is also available in German. This paper presents a major update on the first public version of the corpus released in 2010. This version 2 consists of over 513,091 documents, including more than 9% of new documents retrieved from the United Nations official document system. We applied several modifications to the corpus preparation method. In this paper, we describe the methods we used for processing the UN documents and aligning the sentences. The most significant improvement compared to the previous release is the newly added multilingual sentence alignment information. The alignment information is encoded together with the text in XML instead of additional files. Our representation of the sentence alignment allows quick construction of aligned texts parallel in arbitrary number of languages, which is essential for building machine translation systems.</abstract>
<identifier type="citekey">chen-eisele-2012-multiun</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/641_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2500</start>
<end>2504</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiUN v2: UN Documents with Multilingual Alignments
%A Chen, Yu
%A Eisele, Andreas
%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 chen-eisele-2012-multiun
%X MultiUN is a multilingual parallel corpus extracted from the official documents of the United Nations. It is available in the six official languages of the UN and a small portion of it is also available in German. This paper presents a major update on the first public version of the corpus released in 2010. This version 2 consists of over 513,091 documents, including more than 9% of new documents retrieved from the United Nations official document system. We applied several modifications to the corpus preparation method. In this paper, we describe the methods we used for processing the UN documents and aligning the sentences. The most significant improvement compared to the previous release is the newly added multilingual sentence alignment information. The alignment information is encoded together with the text in XML instead of additional files. Our representation of the sentence alignment allows quick construction of aligned texts parallel in arbitrary number of languages, which is essential for building machine translation systems.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/641_Paper.pdf
%P 2500-2504
Markdown (Informal)
[MultiUN v2: UN Documents with Multilingual Alignments](http://www.lrec-conf.org/proceedings/lrec2012/pdf/641_Paper.pdf) (Chen & Eisele, LREC 2012)
ACL
- Yu Chen and Andreas Eisele. 2012. MultiUN v2: UN Documents with Multilingual Alignments. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2500–2504, Istanbul, Turkey. European Language Resources Association (ELRA).