@inproceedings{pecheux-etal-2014-rule,
title = "Rule-based Reordering Space in Statistical Machine Translation",
author = "P{\'e}cheux, Nicolas and
Allauzen, Alexander and
Yvon, Fran{\c{c}}ois",
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/735_Paper.pdf",
pages = "1800--1806",
abstract = "In Statistical Machine Translation (SMT), the constraints on word reorderings have a great impact on the set of potential translations that are explored. Notwithstanding computationnal issues, the reordering space of a SMT system needs to be designed with great care: if a larger search space is likely to yield better translations, it may also lead to more decoding errors, because of the added ambiguity and the interaction with the pruning strategy. In this paper, we study this trade-off using a state-of-the art translation system, where all reorderings are represented in a word lattice prior to decoding. This allows us to directly explore and compare different reordering spaces. We study in detail a rule-based preordering system, varying the length or number of rules, the tagset used, as well as contrasting with oracle settings and purely combinatorial subsets of permutations. We focus on two language pairs: English-French, a close language pair and English-German, known to be a more challenging reordering pair.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pecheux-etal-2014-rule">
<titleInfo>
<title>Rule-based Reordering Space in Statistical Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Pécheux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Allauzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</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>In Statistical Machine Translation (SMT), the constraints on word reorderings have a great impact on the set of potential translations that are explored. Notwithstanding computationnal issues, the reordering space of a SMT system needs to be designed with great care: if a larger search space is likely to yield better translations, it may also lead to more decoding errors, because of the added ambiguity and the interaction with the pruning strategy. In this paper, we study this trade-off using a state-of-the art translation system, where all reorderings are represented in a word lattice prior to decoding. This allows us to directly explore and compare different reordering spaces. We study in detail a rule-based preordering system, varying the length or number of rules, the tagset used, as well as contrasting with oracle settings and purely combinatorial subsets of permutations. We focus on two language pairs: English-French, a close language pair and English-German, known to be a more challenging reordering pair.</abstract>
<identifier type="citekey">pecheux-etal-2014-rule</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/735_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1800</start>
<end>1806</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rule-based Reordering Space in Statistical Machine Translation
%A Pécheux, Nicolas
%A Allauzen, Alexander
%A Yvon, François
%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 pecheux-etal-2014-rule
%X In Statistical Machine Translation (SMT), the constraints on word reorderings have a great impact on the set of potential translations that are explored. Notwithstanding computationnal issues, the reordering space of a SMT system needs to be designed with great care: if a larger search space is likely to yield better translations, it may also lead to more decoding errors, because of the added ambiguity and the interaction with the pruning strategy. In this paper, we study this trade-off using a state-of-the art translation system, where all reorderings are represented in a word lattice prior to decoding. This allows us to directly explore and compare different reordering spaces. We study in detail a rule-based preordering system, varying the length or number of rules, the tagset used, as well as contrasting with oracle settings and purely combinatorial subsets of permutations. We focus on two language pairs: English-French, a close language pair and English-German, known to be a more challenging reordering pair.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/735_Paper.pdf
%P 1800-1806
Markdown (Informal)
[Rule-based Reordering Space in Statistical Machine Translation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/735_Paper.pdf) (Pécheux et al., LREC 2014)
ACL
- Nicolas Pécheux, Alexander Allauzen, and François Yvon. 2014. Rule-based Reordering Space in Statistical Machine Translation. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1800–1806, Reykjavik, Iceland. European Language Resources Association (ELRA).