@inproceedings{song-etal-2010-enhanced,
title = "Enhanced Infrastructure for Creation and Collection of Translation Resources",
author = "Song, Zhiyi and
Strassel, Stephanie and
Krug, Gary and
Maeda, Kazuaki",
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/798_Paper.pdf",
abstract = "Statistical Machine Translation (MT) systems have achieved impressive results in recent years, due in large part to the increasing availability of parallel text for system training and development. This paper describes recent efforts at Linguistic Data Consortium to create linguistic resources for MT, including corpora, specifications and resource infrastructure. We review LDC's three-pronged ap-proach to parallel text corpus development (acquisition of existing parallel text from known repositories, harvesting and aligning of potential parallel documents from the web, and manual creation of parallel text by professional translators), and describe recent adap-tations that have enabled significant expansions in the scope, variety, quality, efficiency and cost-effectiveness of translation resource creation at LDC.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2010-enhanced">
<titleInfo>
<title>Enhanced Infrastructure for Creation and Collection of Translation Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiyi</namePart>
<namePart type="family">Song</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>
<name type="personal">
<namePart type="given">Gary</namePart>
<namePart type="family">Krug</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuaki</namePart>
<namePart type="family">Maeda</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>Statistical Machine Translation (MT) systems have achieved impressive results in recent years, due in large part to the increasing availability of parallel text for system training and development. This paper describes recent efforts at Linguistic Data Consortium to create linguistic resources for MT, including corpora, specifications and resource infrastructure. We review LDC’s three-pronged ap-proach to parallel text corpus development (acquisition of existing parallel text from known repositories, harvesting and aligning of potential parallel documents from the web, and manual creation of parallel text by professional translators), and describe recent adap-tations that have enabled significant expansions in the scope, variety, quality, efficiency and cost-effectiveness of translation resource creation at LDC.</abstract>
<identifier type="citekey">song-etal-2010-enhanced</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/798_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhanced Infrastructure for Creation and Collection of Translation Resources
%A Song, Zhiyi
%A Strassel, Stephanie
%A Krug, Gary
%A Maeda, Kazuaki
%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 song-etal-2010-enhanced
%X Statistical Machine Translation (MT) systems have achieved impressive results in recent years, due in large part to the increasing availability of parallel text for system training and development. This paper describes recent efforts at Linguistic Data Consortium to create linguistic resources for MT, including corpora, specifications and resource infrastructure. We review LDC’s three-pronged ap-proach to parallel text corpus development (acquisition of existing parallel text from known repositories, harvesting and aligning of potential parallel documents from the web, and manual creation of parallel text by professional translators), and describe recent adap-tations that have enabled significant expansions in the scope, variety, quality, efficiency and cost-effectiveness of translation resource creation at LDC.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/798_Paper.pdf
Markdown (Informal)
[Enhanced Infrastructure for Creation and Collection of Translation Resources](http://www.lrec-conf.org/proceedings/lrec2010/pdf/798_Paper.pdf) (Song et al., LREC 2010)
ACL