@inproceedings{maeda-etal-2008-creating,
title = "Creating Sentence-Aligned Parallel Text Corpora from a Large Archive of Potential Parallel Text using {BITS} and Champollion",
author = "Maeda, Kazuaki and
Ma, Xiaoyi and
Strassel, Stephanie",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/779_paper.pdf",
abstract = "Parallel text is one of the most valuable resources for development of statistical machine translation systems and other NLP applications. The Linguistic Data Consortium (LDC) has supported research on statistical machine translations and other NLP applications by creating and distributing a large amount of parallel text resources for the research communities. However, manual translations are very costly, and the number of known providers that offer complete parallel text is limited. This paper presents a cost effective approach to identify parallel document pairs from sources that provide potential parallel text - namely, sources that may contain whole or partial translations of documents in the source language - using the BITS and Champollion parallel text alignment systems developed by LDC.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maeda-etal-2008-creating">
<titleInfo>
<title>Creating Sentence-Aligned Parallel Text Corpora from a Large Archive of Potential Parallel Text using BITS and Champollion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazuaki</namePart>
<namePart type="family">Maeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyi</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parallel text is one of the most valuable resources for development of statistical machine translation systems and other NLP applications. The Linguistic Data Consortium (LDC) has supported research on statistical machine translations and other NLP applications by creating and distributing a large amount of parallel text resources for the research communities. However, manual translations are very costly, and the number of known providers that offer complete parallel text is limited. This paper presents a cost effective approach to identify parallel document pairs from sources that provide potential parallel text - namely, sources that may contain whole or partial translations of documents in the source language - using the BITS and Champollion parallel text alignment systems developed by LDC.</abstract>
<identifier type="citekey">maeda-etal-2008-creating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/779_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating Sentence-Aligned Parallel Text Corpora from a Large Archive of Potential Parallel Text using BITS and Champollion
%A Maeda, Kazuaki
%A Ma, Xiaoyi
%A Strassel, Stephanie
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F maeda-etal-2008-creating
%X Parallel text is one of the most valuable resources for development of statistical machine translation systems and other NLP applications. The Linguistic Data Consortium (LDC) has supported research on statistical machine translations and other NLP applications by creating and distributing a large amount of parallel text resources for the research communities. However, manual translations are very costly, and the number of known providers that offer complete parallel text is limited. This paper presents a cost effective approach to identify parallel document pairs from sources that provide potential parallel text - namely, sources that may contain whole or partial translations of documents in the source language - using the BITS and Champollion parallel text alignment systems developed by LDC.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/779_paper.pdf
Markdown (Informal)
[Creating Sentence-Aligned Parallel Text Corpora from a Large Archive of Potential Parallel Text using BITS and Champollion](http://www.lrec-conf.org/proceedings/lrec2008/pdf/779_paper.pdf) (Maeda et al., LREC 2008)
ACL