@inproceedings{chen-etal-2008-improving,
title = "Improving Statistical Machine Translation Efficiency by Triangulation",
author = "Chen, Yu and
Eisele, Andreas and
Kay, Martin",
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/733_paper.pdf",
abstract = "In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model that enlarges the search space for the decoder, and consequently requires more time and more resources to translate. This paper describes an attempt to reduce the model size by filtering out the less probable entries based on testing correlation using additional training data in an intermediate third language. The central idea behind the approach is triangulation, the process of incorporating multilingual knowledge in a single system, which eventually utilizes parallel corpora available in more than two languages. We conducted experiments using Europarl corpus to evaluate our approach. The reduction of the model size can be up to 70{\%} while the translation quality is being preserved.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2008-improving">
<titleInfo>
<title>Improving Statistical Machine Translation Efficiency by Triangulation</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>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Kay</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>In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model that enlarges the search space for the decoder, and consequently requires more time and more resources to translate. This paper describes an attempt to reduce the model size by filtering out the less probable entries based on testing correlation using additional training data in an intermediate third language. The central idea behind the approach is triangulation, the process of incorporating multilingual knowledge in a single system, which eventually utilizes parallel corpora available in more than two languages. We conducted experiments using Europarl corpus to evaluate our approach. The reduction of the model size can be up to 70% while the translation quality is being preserved.</abstract>
<identifier type="citekey">chen-etal-2008-improving</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/733_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Statistical Machine Translation Efficiency by Triangulation
%A Chen, Yu
%A Eisele, Andreas
%A Kay, Martin
%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 chen-etal-2008-improving
%X In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model that enlarges the search space for the decoder, and consequently requires more time and more resources to translate. This paper describes an attempt to reduce the model size by filtering out the less probable entries based on testing correlation using additional training data in an intermediate third language. The central idea behind the approach is triangulation, the process of incorporating multilingual knowledge in a single system, which eventually utilizes parallel corpora available in more than two languages. We conducted experiments using Europarl corpus to evaluate our approach. The reduction of the model size can be up to 70% while the translation quality is being preserved.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/733_paper.pdf
Markdown (Informal)
[Improving Statistical Machine Translation Efficiency by Triangulation](http://www.lrec-conf.org/proceedings/lrec2008/pdf/733_paper.pdf) (Chen et al., LREC 2008)
ACL