@inproceedings{su-babych-2012-development,
title = "Development and Application of a Cross-language Document Comparability Metric",
author = "Su, Fangzhong and
Babych, Bogdan",
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/804_Paper.pdf",
pages = "3956--3962",
abstract = "In this paper we present a metric that measures comparability of documents across different languages. The metric is developed within the FP7 ICT ACCURAT project, as a tool for aligning comparable corpora on the document level; further these aligned comparable documents are used for phrase alignment and extraction of translation equivalents, with the aim to extend phrase tables of statistical MT systems without the need to use parallel texts. The metric uses several features, such as lexical information, document structure, keywords and named entities, which are combined in an ensemble manner. We present the results by measuring the reliability and effectiveness of the metric, and demonstrate its application and the impact for the task of parallel phrase extraction from comparable corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="su-babych-2012-development">
<titleInfo>
<title>Development and Application of a Cross-language Document Comparability Metric</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fangzhong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bogdan</namePart>
<namePart type="family">Babych</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>In this paper we present a metric that measures comparability of documents across different languages. The metric is developed within the FP7 ICT ACCURAT project, as a tool for aligning comparable corpora on the document level; further these aligned comparable documents are used for phrase alignment and extraction of translation equivalents, with the aim to extend phrase tables of statistical MT systems without the need to use parallel texts. The metric uses several features, such as lexical information, document structure, keywords and named entities, which are combined in an ensemble manner. We present the results by measuring the reliability and effectiveness of the metric, and demonstrate its application and the impact for the task of parallel phrase extraction from comparable corpora.</abstract>
<identifier type="citekey">su-babych-2012-development</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/804_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3956</start>
<end>3962</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development and Application of a Cross-language Document Comparability Metric
%A Su, Fangzhong
%A Babych, Bogdan
%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 su-babych-2012-development
%X In this paper we present a metric that measures comparability of documents across different languages. The metric is developed within the FP7 ICT ACCURAT project, as a tool for aligning comparable corpora on the document level; further these aligned comparable documents are used for phrase alignment and extraction of translation equivalents, with the aim to extend phrase tables of statistical MT systems without the need to use parallel texts. The metric uses several features, such as lexical information, document structure, keywords and named entities, which are combined in an ensemble manner. We present the results by measuring the reliability and effectiveness of the metric, and demonstrate its application and the impact for the task of parallel phrase extraction from comparable corpora.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/804_Paper.pdf
%P 3956-3962
Markdown (Informal)
[Development and Application of a Cross-language Document Comparability Metric](http://www.lrec-conf.org/proceedings/lrec2012/pdf/804_Paper.pdf) (Su & Babych, LREC 2012)
ACL