@inproceedings{costa-jussa-etal-2008-using,
title = "Using Reordering in Statistical Machine Translation based on Alignment Block Classification",
author = "Costa-juss{\`a}, Marta R. and
Fonollosa, Jos{\'e} A. R. and
Monte, Enric",
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/444_paper.pdf",
abstract = "Statistical Machine Translation (SMT) is based on alignment models which learn from bilingual corpora the word correspondences between source and target language. These models are assumed to be capable of learning reorderings of sequences of words. However, the difference in word order between two languages is one of the most important sources of errors in SMT. This paper proposes a Recursive Alignment Block Classification algorithm (RABCA) that can take advantage of inductive learning in order to solve reordering problems. This algorithm should be able to cope with swapping examples seen during training; it should infer properties that might permit to reorder pairs of blocks (sequences of words) which did not appear during training; and finally it should be robust with respect to training errors and ambiguities. Experiments are reported on the EuroParl task and RABCA is tested using two state-of-the-art SMT systems: a phrased-based and an Ngram-based. In both cases, RABCA improves results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="costa-jussa-etal-2008-using">
<titleInfo>
<title>Using Reordering in Statistical Machine Translation based on Alignment Block Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">A</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Fonollosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enric</namePart>
<namePart type="family">Monte</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>Statistical Machine Translation (SMT) is based on alignment models which learn from bilingual corpora the word correspondences between source and target language. These models are assumed to be capable of learning reorderings of sequences of words. However, the difference in word order between two languages is one of the most important sources of errors in SMT. This paper proposes a Recursive Alignment Block Classification algorithm (RABCA) that can take advantage of inductive learning in order to solve reordering problems. This algorithm should be able to cope with swapping examples seen during training; it should infer properties that might permit to reorder pairs of blocks (sequences of words) which did not appear during training; and finally it should be robust with respect to training errors and ambiguities. Experiments are reported on the EuroParl task and RABCA is tested using two state-of-the-art SMT systems: a phrased-based and an Ngram-based. In both cases, RABCA improves results.</abstract>
<identifier type="citekey">costa-jussa-etal-2008-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/444_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Reordering in Statistical Machine Translation based on Alignment Block Classification
%A Costa-jussà, Marta R.
%A Fonollosa, José A. R.
%A Monte, Enric
%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 costa-jussa-etal-2008-using
%X Statistical Machine Translation (SMT) is based on alignment models which learn from bilingual corpora the word correspondences between source and target language. These models are assumed to be capable of learning reorderings of sequences of words. However, the difference in word order between two languages is one of the most important sources of errors in SMT. This paper proposes a Recursive Alignment Block Classification algorithm (RABCA) that can take advantage of inductive learning in order to solve reordering problems. This algorithm should be able to cope with swapping examples seen during training; it should infer properties that might permit to reorder pairs of blocks (sequences of words) which did not appear during training; and finally it should be robust with respect to training errors and ambiguities. Experiments are reported on the EuroParl task and RABCA is tested using two state-of-the-art SMT systems: a phrased-based and an Ngram-based. In both cases, RABCA improves results.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/444_paper.pdf
Markdown (Informal)
[Using Reordering in Statistical Machine Translation based on Alignment Block Classification](http://www.lrec-conf.org/proceedings/lrec2008/pdf/444_paper.pdf) (Costa-jussà et al., LREC 2008)
ACL