@inproceedings{kusumoto-akiba-2012-statistical,
title = "Statistical Machine Translation without Source-side Parallel Corpus Using Word Lattice and Phrase Extension",
author = "Kusumoto, Takanori and
Akiba, Tomoyosi",
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/677_Paper.pdf",
pages = "3929--3932",
abstract = "Statistical machine translation (SMT) requires a parallel corpus between the source and target languages. Although a pivot-translation approach can be applied to a language pair that does not have a parallel corpus directly between them, it requires both source―pivot and pivot―target parallel corpora. We propose a novel approach to apply SMT to a resource-limited source language that has no parallel corpus but has only a word dictionary for the pivot language. The problems with dictionary-based translations lie in their ambiguity and incompleteness. The proposed method uses a word lattice representation of the pivot-language candidates and word lattice decoding to deal with the ambiguity; the lattice expansion is accomplished by using a pivot―target phrase translation table to compensate for the incompleteness. Our experimental evaluation showed that this approach is promising for applying SMT, even when a source-side parallel corpus is lacking.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kusumoto-akiba-2012-statistical">
<titleInfo>
<title>Statistical Machine Translation without Source-side Parallel Corpus Using Word Lattice and Phrase Extension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Takanori</namePart>
<namePart type="family">Kusumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyosi</namePart>
<namePart type="family">Akiba</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>Statistical machine translation (SMT) requires a parallel corpus between the source and target languages. Although a pivot-translation approach can be applied to a language pair that does not have a parallel corpus directly between them, it requires both source―pivot and pivot―target parallel corpora. We propose a novel approach to apply SMT to a resource-limited source language that has no parallel corpus but has only a word dictionary for the pivot language. The problems with dictionary-based translations lie in their ambiguity and incompleteness. The proposed method uses a word lattice representation of the pivot-language candidates and word lattice decoding to deal with the ambiguity; the lattice expansion is accomplished by using a pivot―target phrase translation table to compensate for the incompleteness. Our experimental evaluation showed that this approach is promising for applying SMT, even when a source-side parallel corpus is lacking.</abstract>
<identifier type="citekey">kusumoto-akiba-2012-statistical</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/677_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3929</start>
<end>3932</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Statistical Machine Translation without Source-side Parallel Corpus Using Word Lattice and Phrase Extension
%A Kusumoto, Takanori
%A Akiba, Tomoyosi
%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 kusumoto-akiba-2012-statistical
%X Statistical machine translation (SMT) requires a parallel corpus between the source and target languages. Although a pivot-translation approach can be applied to a language pair that does not have a parallel corpus directly between them, it requires both source―pivot and pivot―target parallel corpora. We propose a novel approach to apply SMT to a resource-limited source language that has no parallel corpus but has only a word dictionary for the pivot language. The problems with dictionary-based translations lie in their ambiguity and incompleteness. The proposed method uses a word lattice representation of the pivot-language candidates and word lattice decoding to deal with the ambiguity; the lattice expansion is accomplished by using a pivot―target phrase translation table to compensate for the incompleteness. Our experimental evaluation showed that this approach is promising for applying SMT, even when a source-side parallel corpus is lacking.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/677_Paper.pdf
%P 3929-3932
Markdown (Informal)
[Statistical Machine Translation without Source-side Parallel Corpus Using Word Lattice and Phrase Extension](http://www.lrec-conf.org/proceedings/lrec2012/pdf/677_Paper.pdf) (Kusumoto & Akiba, LREC 2012)
ACL