@inproceedings{itagaki-aikawa-2008-post,
title = "Post-{MT} Term Swapper: Supplementing a Statistical Machine Translation System with a User Dictionary",
author = "Itagaki, Masaki and
Aikawa, Takako",
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/403_paper.pdf",
abstract = "A statistical machine translation (SMT) system requires homogeneous training data in order to get domain-sensitive (or context-sensitive) terminology translations. If the data contains various domains, it is difficult for an SMT to learn context-sensitive terminology mappings probabilistically. Yet, terminology translation accuracy is an important issue for MT users. This paper explores an approach to tackle this terminology translation problem for an SMT. We propose a way to identify terminology translations from MT output and automatically swap them with user-defined translations. Our approach is simple and can be applied to any type of MT system. We call our prototype Term Swapper. Term Swapper allows MT users to draw on their own dictionaries without affecting any parts of the MT output except for the terminology translation(s) in question. Using an SMT developed at Microsoft Research, called MSR-MT (Quirk et al., (2005); Menezes {\&} Quirk (2005)), we conducted initial experiments to investigate the coverage rate of Term Swapper and its impact on the overall quality of MT output. The results from our experiments show high coverage and positive impact on the overall MT quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="itagaki-aikawa-2008-post">
<titleInfo>
<title>Post-MT Term Swapper: Supplementing a Statistical Machine Translation System with a User Dictionary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masaki</namePart>
<namePart type="family">Itagaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takako</namePart>
<namePart type="family">Aikawa</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>A statistical machine translation (SMT) system requires homogeneous training data in order to get domain-sensitive (or context-sensitive) terminology translations. If the data contains various domains, it is difficult for an SMT to learn context-sensitive terminology mappings probabilistically. Yet, terminology translation accuracy is an important issue for MT users. This paper explores an approach to tackle this terminology translation problem for an SMT. We propose a way to identify terminology translations from MT output and automatically swap them with user-defined translations. Our approach is simple and can be applied to any type of MT system. We call our prototype Term Swapper. Term Swapper allows MT users to draw on their own dictionaries without affecting any parts of the MT output except for the terminology translation(s) in question. Using an SMT developed at Microsoft Research, called MSR-MT (Quirk et al., (2005); Menezes & Quirk (2005)), we conducted initial experiments to investigate the coverage rate of Term Swapper and its impact on the overall quality of MT output. The results from our experiments show high coverage and positive impact on the overall MT quality.</abstract>
<identifier type="citekey">itagaki-aikawa-2008-post</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/403_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Post-MT Term Swapper: Supplementing a Statistical Machine Translation System with a User Dictionary
%A Itagaki, Masaki
%A Aikawa, Takako
%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 itagaki-aikawa-2008-post
%X A statistical machine translation (SMT) system requires homogeneous training data in order to get domain-sensitive (or context-sensitive) terminology translations. If the data contains various domains, it is difficult for an SMT to learn context-sensitive terminology mappings probabilistically. Yet, terminology translation accuracy is an important issue for MT users. This paper explores an approach to tackle this terminology translation problem for an SMT. We propose a way to identify terminology translations from MT output and automatically swap them with user-defined translations. Our approach is simple and can be applied to any type of MT system. We call our prototype Term Swapper. Term Swapper allows MT users to draw on their own dictionaries without affecting any parts of the MT output except for the terminology translation(s) in question. Using an SMT developed at Microsoft Research, called MSR-MT (Quirk et al., (2005); Menezes & Quirk (2005)), we conducted initial experiments to investigate the coverage rate of Term Swapper and its impact on the overall quality of MT output. The results from our experiments show high coverage and positive impact on the overall MT quality.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/403_paper.pdf
Markdown (Informal)
[Post-MT Term Swapper: Supplementing a Statistical Machine Translation System with a User Dictionary](http://www.lrec-conf.org/proceedings/lrec2008/pdf/403_paper.pdf) (Itagaki & Aikawa, LREC 2008)
ACL