@inproceedings{loaiciga-etal-2014-english,
title = "{E}nglish-{F}rench Verb Phrase Alignment in {E}uroparl for Tense Translation Modeling",
author = "Lo{\'a}iciga, Sharid and
Meyer, Thomas and
Popescu-Belis, Andrei",
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/205_Paper.pdf",
pages = "674--681",
abstract = "This paper presents a method for verb phrase (VP) alignment in an English-French parallel corpus and its use for improving statistical machine translation (SMT) of verb tenses. The method starts from automatic word alignment performed with GIZA++, and relies on a POS tagger and a parser, in combination with several heuristics, in order to identify non-contiguous components of VPs, and to label the aligned VPs with their tense and voice on each side. This procedure is applied to the Europarl corpus, leading to the creation of a smaller, high-precision parallel corpus with about 320,000 pairs of finite VPs, which is made publicly available. This resource is used to train a tense predictor for translation from English into French, based on a large number of surface features. Three MT systems are compared: (1) a baseline phrase-based SMT; (2) a tense-aware SMT system using the above predictions within a factored translation model; and (3) a system using oracle predictions from the aligned VPs. For several tenses, such as the French {``}imparfait{''}, the tense-aware SMT system improves significantly over the baseline and is closer to the oracle system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="loaiciga-etal-2014-english">
<titleInfo>
<title>English-French Verb Phrase Alignment in Europarl for Tense Translation Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loáiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Meyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Popescu-Belis</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>This paper presents a method for verb phrase (VP) alignment in an English-French parallel corpus and its use for improving statistical machine translation (SMT) of verb tenses. The method starts from automatic word alignment performed with GIZA++, and relies on a POS tagger and a parser, in combination with several heuristics, in order to identify non-contiguous components of VPs, and to label the aligned VPs with their tense and voice on each side. This procedure is applied to the Europarl corpus, leading to the creation of a smaller, high-precision parallel corpus with about 320,000 pairs of finite VPs, which is made publicly available. This resource is used to train a tense predictor for translation from English into French, based on a large number of surface features. Three MT systems are compared: (1) a baseline phrase-based SMT; (2) a tense-aware SMT system using the above predictions within a factored translation model; and (3) a system using oracle predictions from the aligned VPs. For several tenses, such as the French “imparfait”, the tense-aware SMT system improves significantly over the baseline and is closer to the oracle system.</abstract>
<identifier type="citekey">loaiciga-etal-2014-english</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/205_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>674</start>
<end>681</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T English-French Verb Phrase Alignment in Europarl for Tense Translation Modeling
%A Loáiciga, Sharid
%A Meyer, Thomas
%A Popescu-Belis, Andrei
%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 loaiciga-etal-2014-english
%X This paper presents a method for verb phrase (VP) alignment in an English-French parallel corpus and its use for improving statistical machine translation (SMT) of verb tenses. The method starts from automatic word alignment performed with GIZA++, and relies on a POS tagger and a parser, in combination with several heuristics, in order to identify non-contiguous components of VPs, and to label the aligned VPs with their tense and voice on each side. This procedure is applied to the Europarl corpus, leading to the creation of a smaller, high-precision parallel corpus with about 320,000 pairs of finite VPs, which is made publicly available. This resource is used to train a tense predictor for translation from English into French, based on a large number of surface features. Three MT systems are compared: (1) a baseline phrase-based SMT; (2) a tense-aware SMT system using the above predictions within a factored translation model; and (3) a system using oracle predictions from the aligned VPs. For several tenses, such as the French “imparfait”, the tense-aware SMT system improves significantly over the baseline and is closer to the oracle system.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/205_Paper.pdf
%P 674-681
Markdown (Informal)
[English-French Verb Phrase Alignment in Europarl for Tense Translation Modeling](http://www.lrec-conf.org/proceedings/lrec2014/pdf/205_Paper.pdf) (Loáiciga et al., LREC 2014)
ACL