@inproceedings{carpuat-etal-2010-reordering,
title = "Reordering Matrix Post-verbal Subjects for {A}rabic-to-{E}nglish {SMT}",
author = "Carpuat, Marine and
Marton, Yuval and
Habash, Nizar",
editor = "Langlais, Philippe and
Gagnon, Michel",
booktitle = "Actes de la 17e conf{\'e}rence sur le Traitement Automatique des Langues Naturelles. Articles longs",
month = jul,
year = "2010",
address = "Montr{\'e}al, Canada",
publisher = "ATALA",
url = "https://aclanthology.org/2010.jeptalnrecital-long.30/",
pages = "292--301",
abstract = "We improve our recently proposed technique for integrating Arabic verb-subject constructions in SMT word alignment (Carpuat et al., 2010) by distinguishing between matrix (or main clause) and non-matrix Arabic verb-subject constructions. In gold translations, most matrix VS (main clause verb-subject) constructions are translated in inverted SV order, while non-matrix (subordinate clause) VS constructions are inverted in only half the cases. In addition, while detecting verbs and their subjects is a hard task, our syntactic parser detects VS constructions better in matrix than in non-matrix clauses. As a result, reordering only matrix VS for word alignment consistently improves translation quality over a phrase-based SMT baseline, and over reordering all VS constructions, in both medium- and large-scale settings. In fact, the improvements obtained by reordering matrix VS on the medium-scale setting remarkably represent 44{\%} of the gain in BLEU and 51{\%} of the gain in TER obtained with a word alignment training bitext that is 5 times larger."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carpuat-etal-2010-reordering">
<titleInfo>
<title>Reordering Matrix Post-verbal Subjects for Arabic-to-English SMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Marton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes de la 17e conférence sur le Traitement Automatique des Langues Naturelles. Articles longs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Langlais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Gagnon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA</publisher>
<place>
<placeTerm type="text">Montréal, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We improve our recently proposed technique for integrating Arabic verb-subject constructions in SMT word alignment (Carpuat et al., 2010) by distinguishing between matrix (or main clause) and non-matrix Arabic verb-subject constructions. In gold translations, most matrix VS (main clause verb-subject) constructions are translated in inverted SV order, while non-matrix (subordinate clause) VS constructions are inverted in only half the cases. In addition, while detecting verbs and their subjects is a hard task, our syntactic parser detects VS constructions better in matrix than in non-matrix clauses. As a result, reordering only matrix VS for word alignment consistently improves translation quality over a phrase-based SMT baseline, and over reordering all VS constructions, in both medium- and large-scale settings. In fact, the improvements obtained by reordering matrix VS on the medium-scale setting remarkably represent 44% of the gain in BLEU and 51% of the gain in TER obtained with a word alignment training bitext that is 5 times larger.</abstract>
<identifier type="citekey">carpuat-etal-2010-reordering</identifier>
<location>
<url>https://aclanthology.org/2010.jeptalnrecital-long.30/</url>
</location>
<part>
<date>2010-07</date>
<extent unit="page">
<start>292</start>
<end>301</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reordering Matrix Post-verbal Subjects for Arabic-to-English SMT
%A Carpuat, Marine
%A Marton, Yuval
%A Habash, Nizar
%Y Langlais, Philippe
%Y Gagnon, Michel
%S Actes de la 17e conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
%D 2010
%8 July
%I ATALA
%C Montréal, Canada
%F carpuat-etal-2010-reordering
%X We improve our recently proposed technique for integrating Arabic verb-subject constructions in SMT word alignment (Carpuat et al., 2010) by distinguishing between matrix (or main clause) and non-matrix Arabic verb-subject constructions. In gold translations, most matrix VS (main clause verb-subject) constructions are translated in inverted SV order, while non-matrix (subordinate clause) VS constructions are inverted in only half the cases. In addition, while detecting verbs and their subjects is a hard task, our syntactic parser detects VS constructions better in matrix than in non-matrix clauses. As a result, reordering only matrix VS for word alignment consistently improves translation quality over a phrase-based SMT baseline, and over reordering all VS constructions, in both medium- and large-scale settings. In fact, the improvements obtained by reordering matrix VS on the medium-scale setting remarkably represent 44% of the gain in BLEU and 51% of the gain in TER obtained with a word alignment training bitext that is 5 times larger.
%U https://aclanthology.org/2010.jeptalnrecital-long.30/
%P 292-301
Markdown (Informal)
[Reordering Matrix Post-verbal Subjects for Arabic-to-English SMT](https://aclanthology.org/2010.jeptalnrecital-long.30/) (Carpuat et al., JEP/TALN/RECITAL 2010)
ACL