@inproceedings{jaja-etal-2012-assessing,
title = "Assessing Divergence Measures for Automated Document Routing in an Adaptive {MT} System",
author = "Jaja, Claire and
Briesch, Douglas and
Laoudi, Jamal and
Voss, Clare",
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/843_Paper.pdf",
pages = "3963--3970",
abstract = "Custom machine translation (MT) engines systematically outperform general-domain MT engines when translating within the relevant custom domain. This paper investigates the use of the Jensen-Shannon divergence measure for automatically routing new documents within a translation system with multiple MT engines to the appropriate custom MT engine in order to obtain the best translation. Three distinct domains are compared, and the impact of the language, size, and preprocessing of the documents on the Jensen-Shannon score is addressed. Six test datasets are then compared to the three known-domain corpora to predict which of the three custom MT engines they would be routed to at runtime given their Jensen-Shannon scores. The results are promising for incorporating this divergence measure into a translation workflow.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jaja-etal-2012-assessing">
<titleInfo>
<title>Assessing Divergence Measures for Automated Document Routing in an Adaptive MT System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Jaja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="family">Briesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamal</namePart>
<namePart type="family">Laoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clare</namePart>
<namePart type="family">Voss</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>Custom machine translation (MT) engines systematically outperform general-domain MT engines when translating within the relevant custom domain. This paper investigates the use of the Jensen-Shannon divergence measure for automatically routing new documents within a translation system with multiple MT engines to the appropriate custom MT engine in order to obtain the best translation. Three distinct domains are compared, and the impact of the language, size, and preprocessing of the documents on the Jensen-Shannon score is addressed. Six test datasets are then compared to the three known-domain corpora to predict which of the three custom MT engines they would be routed to at runtime given their Jensen-Shannon scores. The results are promising for incorporating this divergence measure into a translation workflow.</abstract>
<identifier type="citekey">jaja-etal-2012-assessing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/843_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3963</start>
<end>3970</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing Divergence Measures for Automated Document Routing in an Adaptive MT System
%A Jaja, Claire
%A Briesch, Douglas
%A Laoudi, Jamal
%A Voss, Clare
%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 jaja-etal-2012-assessing
%X Custom machine translation (MT) engines systematically outperform general-domain MT engines when translating within the relevant custom domain. This paper investigates the use of the Jensen-Shannon divergence measure for automatically routing new documents within a translation system with multiple MT engines to the appropriate custom MT engine in order to obtain the best translation. Three distinct domains are compared, and the impact of the language, size, and preprocessing of the documents on the Jensen-Shannon score is addressed. Six test datasets are then compared to the three known-domain corpora to predict which of the three custom MT engines they would be routed to at runtime given their Jensen-Shannon scores. The results are promising for incorporating this divergence measure into a translation workflow.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/843_Paper.pdf
%P 3963-3970
Markdown (Informal)
[Assessing Divergence Measures for Automated Document Routing in an Adaptive MT System](http://www.lrec-conf.org/proceedings/lrec2012/pdf/843_Paper.pdf) (Jaja et al., LREC 2012)
ACL