@inproceedings{mauser-etal-2006-training,
title = "Training a Statistical Machine Translation System without {GIZA}++",
author = "Mauser, Arne and
Matusov, Evgeny and
Ney, Hermann",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/320_pdf.pdf",
abstract = "The IBM Models (Brown et al., 1993) enjoy great popularity in the machine translation community because they offer high quality word alignments and a free implementation is available with the GIZA++ Toolkit (Och and Ney, 2003). Several methods have been developed to overcome the asymmetry of the alignment generated by the IBM Models. A remaining disadvantage, however, is the high model complexity. This paper describes a word alignment training procedure for statistical machine translation that uses a simple and clear statistical model, different from the IBM models. The main idea of the algorithm is to generate a symmetric and monotonic alignment between the target sentence and a permutation graph representing different reorderings of the words in the source sentence. The quality of the generated alignment is shown to be comparable to the standard GIZA++ training in an SMT setup.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mauser-etal-2006-training">
<titleInfo>
<title>Training a Statistical Machine Translation System without GIZA++</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arne</namePart>
<namePart type="family">Mauser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgeny</namePart>
<namePart type="family">Matusov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hermann</namePart>
<namePart type="family">Ney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The IBM Models (Brown et al., 1993) enjoy great popularity in the machine translation community because they offer high quality word alignments and a free implementation is available with the GIZA++ Toolkit (Och and Ney, 2003). Several methods have been developed to overcome the asymmetry of the alignment generated by the IBM Models. A remaining disadvantage, however, is the high model complexity. This paper describes a word alignment training procedure for statistical machine translation that uses a simple and clear statistical model, different from the IBM models. The main idea of the algorithm is to generate a symmetric and monotonic alignment between the target sentence and a permutation graph representing different reorderings of the words in the source sentence. The quality of the generated alignment is shown to be comparable to the standard GIZA++ training in an SMT setup.</abstract>
<identifier type="citekey">mauser-etal-2006-training</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/320_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training a Statistical Machine Translation System without GIZA++
%A Mauser, Arne
%A Matusov, Evgeny
%A Ney, Hermann
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F mauser-etal-2006-training
%X The IBM Models (Brown et al., 1993) enjoy great popularity in the machine translation community because they offer high quality word alignments and a free implementation is available with the GIZA++ Toolkit (Och and Ney, 2003). Several methods have been developed to overcome the asymmetry of the alignment generated by the IBM Models. A remaining disadvantage, however, is the high model complexity. This paper describes a word alignment training procedure for statistical machine translation that uses a simple and clear statistical model, different from the IBM models. The main idea of the algorithm is to generate a symmetric and monotonic alignment between the target sentence and a permutation graph representing different reorderings of the words in the source sentence. The quality of the generated alignment is shown to be comparable to the standard GIZA++ training in an SMT setup.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/320_pdf.pdf
Markdown (Informal)
[Training a Statistical Machine Translation System without GIZA++](http://www.lrec-conf.org/proceedings/lrec2006/pdf/320_pdf.pdf) (Mauser et al., LREC 2006)
ACL