@inproceedings{sangodkar-damani-2012-ordering,
title = "Re-ordering Source Sentences for {SMT}",
author = "Sangodkar, Amit and
Damani, Om",
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/340_Paper.pdf",
pages = "2164--2171",
abstract = "We propose a pre-processing stage for Statistical Machine Translation (SMT) systems where the words of the source sentence are re-ordered as per the syntax of the target language prior to the alignment process, so that the alignment found by the statistical system is improved. We take a dependency parse of the source sentence and linearize it as per the syntax of the target language, before it is used in either the training or the decoding phase. During this linearization, the ordering decisions among dependency nodes having a common parent are done based on two aspects: parent-child positioning and relation priority. To make the linearization process rule-driven, we assume that the relative word order of a dependency relation's relata does not depend either on the semantic properties of the relata or on the rest of the expression. We also assume that the relative word order of various relations sharing a relata does not depend on the rest of the expression. We experiment with a publicly available English-Hindi parallel corpus and show that our scheme improves the BLEU score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sangodkar-damani-2012-ordering">
<titleInfo>
<title>Re-ordering Source Sentences for SMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Sangodkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Om</namePart>
<namePart type="family">Damani</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>We propose a pre-processing stage for Statistical Machine Translation (SMT) systems where the words of the source sentence are re-ordered as per the syntax of the target language prior to the alignment process, so that the alignment found by the statistical system is improved. We take a dependency parse of the source sentence and linearize it as per the syntax of the target language, before it is used in either the training or the decoding phase. During this linearization, the ordering decisions among dependency nodes having a common parent are done based on two aspects: parent-child positioning and relation priority. To make the linearization process rule-driven, we assume that the relative word order of a dependency relation’s relata does not depend either on the semantic properties of the relata or on the rest of the expression. We also assume that the relative word order of various relations sharing a relata does not depend on the rest of the expression. We experiment with a publicly available English-Hindi parallel corpus and show that our scheme improves the BLEU score.</abstract>
<identifier type="citekey">sangodkar-damani-2012-ordering</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/340_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2164</start>
<end>2171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Re-ordering Source Sentences for SMT
%A Sangodkar, Amit
%A Damani, Om
%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 sangodkar-damani-2012-ordering
%X We propose a pre-processing stage for Statistical Machine Translation (SMT) systems where the words of the source sentence are re-ordered as per the syntax of the target language prior to the alignment process, so that the alignment found by the statistical system is improved. We take a dependency parse of the source sentence and linearize it as per the syntax of the target language, before it is used in either the training or the decoding phase. During this linearization, the ordering decisions among dependency nodes having a common parent are done based on two aspects: parent-child positioning and relation priority. To make the linearization process rule-driven, we assume that the relative word order of a dependency relation’s relata does not depend either on the semantic properties of the relata or on the rest of the expression. We also assume that the relative word order of various relations sharing a relata does not depend on the rest of the expression. We experiment with a publicly available English-Hindi parallel corpus and show that our scheme improves the BLEU score.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/340_Paper.pdf
%P 2164-2171
Markdown (Informal)
[Re-ordering Source Sentences for SMT](http://www.lrec-conf.org/proceedings/lrec2012/pdf/340_Paper.pdf) (Sangodkar & Damani, LREC 2012)
ACL
- Amit Sangodkar and Om Damani. 2012. Re-ordering Source Sentences for SMT. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2164–2171, Istanbul, Turkey. European Language Resources Association (ELRA).