@inproceedings{pal-etal-2014-word,
title = "Word Alignment-Based Reordering of Source Chunks in {PB}-{SMT}",
author = "Pal, Santanu and
Naskar, Sudip Kumar and
Bandyopadhyay, Sivaji",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/982_Paper.pdf",
abstract = "Reordering poses a big challenge in statistical machine translation between distant language pairs. The paper presents how reordering between distant language pairs can be handled efficiently in phrase-based statistical machine translation. The problem of reordering between distant languages has been approached with prior reordering of the source text at chunk level to simulate the target language ordering. Prior reordering of the source chunks is performed in the present work by following the target word order suggested by word alignment. The testset is reordered using monolingual MT trained on source and reordered source. This approach of prior reordering of the source chunks was compared with pre-ordering of source words based on word alignments and the traditional approach of prior source reordering based on language-pair specific reordering rules. The effects of these reordering approaches were studied on an English{--}Bengali translation task, a language pair with different word order. From the experimental results it was found that word alignment based reordering of the source chunks is more effective than the other reordering approaches, and it produces statistically significant improvements over the baseline system on BLEU. On manual inspection we found significant improvements in terms of word alignments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pal-etal-2014-word">
<titleInfo>
<title>Word Alignment-Based Reordering of Source Chunks in PB-SMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santanu</namePart>
<namePart type="family">Pal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudip</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Naskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Reordering poses a big challenge in statistical machine translation between distant language pairs. The paper presents how reordering between distant language pairs can be handled efficiently in phrase-based statistical machine translation. The problem of reordering between distant languages has been approached with prior reordering of the source text at chunk level to simulate the target language ordering. Prior reordering of the source chunks is performed in the present work by following the target word order suggested by word alignment. The testset is reordered using monolingual MT trained on source and reordered source. This approach of prior reordering of the source chunks was compared with pre-ordering of source words based on word alignments and the traditional approach of prior source reordering based on language-pair specific reordering rules. The effects of these reordering approaches were studied on an English–Bengali translation task, a language pair with different word order. From the experimental results it was found that word alignment based reordering of the source chunks is more effective than the other reordering approaches, and it produces statistically significant improvements over the baseline system on BLEU. On manual inspection we found significant improvements in terms of word alignments.</abstract>
<identifier type="citekey">pal-etal-2014-word</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/982_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Alignment-Based Reordering of Source Chunks in PB-SMT
%A Pal, Santanu
%A Naskar, Sudip Kumar
%A Bandyopadhyay, Sivaji
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F pal-etal-2014-word
%X Reordering poses a big challenge in statistical machine translation between distant language pairs. The paper presents how reordering between distant language pairs can be handled efficiently in phrase-based statistical machine translation. The problem of reordering between distant languages has been approached with prior reordering of the source text at chunk level to simulate the target language ordering. Prior reordering of the source chunks is performed in the present work by following the target word order suggested by word alignment. The testset is reordered using monolingual MT trained on source and reordered source. This approach of prior reordering of the source chunks was compared with pre-ordering of source words based on word alignments and the traditional approach of prior source reordering based on language-pair specific reordering rules. The effects of these reordering approaches were studied on an English–Bengali translation task, a language pair with different word order. From the experimental results it was found that word alignment based reordering of the source chunks is more effective than the other reordering approaches, and it produces statistically significant improvements over the baseline system on BLEU. On manual inspection we found significant improvements in terms of word alignments.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/982_Paper.pdf
Markdown (Informal)
[Word Alignment-Based Reordering of Source Chunks in PB-SMT](http://www.lrec-conf.org/proceedings/lrec2014/pdf/982_Paper.pdf) (Pal et al., LREC 2014)
ACL
- Santanu Pal, Sudip Kumar Naskar, and Sivaji Bandyopadhyay. 2014. Word Alignment-Based Reordering of Source Chunks in PB-SMT. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), Reykjavik, Iceland. European Language Resources Association (ELRA).