<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gosme-etal-2010-greyc">
    <titleInfo>
        <title>The GREYC/LLACAN machine translation systems for the IWSLT 2010 campaign</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Julien</namePart>
        <namePart type="family">Gosme</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wigdan</namePart>
        <namePart type="family">Mekki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fathi</namePart>
        <namePart type="family">Debili</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yves</namePart>
        <namePart type="family">Lepage</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nadine</namePart>
        <namePart type="family">Lucas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2010-dec&quot; 2-3&quot;</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign</title>
        </titleInfo>
        <originInfo>
            <place>
                <placeTerm type="text">Paris, France</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper we explore the contribution of the use of two Arabic morphological analyzers as preprocessing tools for statistical machine translation. Similar investigations have already been reported for morphologically rich languages like German, Turkish and Arabic. Here, we focus on the case of the Arabic language and mainly discuss the use of the G-LexAr analyzer. A preliminary experiment has been designed to choose the most promising translation system among the 3 G-LexAr-based systems, we concluded that the systems are equivalent. Nevertheless, we decided to use the lemmatized output of G-LexAr and use its translations as primary run for the BTEC AE track. The results showed that G-LexAr outputs degrades translation compared to the basic SMT system trained on the un-analyzed corpus.</abstract>
    <identifier type="citekey">gosme-etal-2010-greyc</identifier>
    <location>
        <url>https://aclanthology.org/2010.iwslt-evaluation.6</url>
    </location>
    <part>
        <date>2010-dec&quot; 2-3&quot;</date>
        <extent unit="page">
            <start>59</start>
            <end>65</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The GREYC/LLACAN machine translation systems for the IWSLT 2010 campaign
%A Gosme, Julien
%A Mekki, Wigdan
%A Debili, Fathi
%A Lepage, Yves
%A Lucas, Nadine
%S Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign
%D 2010
%8 dec" 2 3"
%C Paris, France
%F gosme-etal-2010-greyc
%X In this paper we explore the contribution of the use of two Arabic morphological analyzers as preprocessing tools for statistical machine translation. Similar investigations have already been reported for morphologically rich languages like German, Turkish and Arabic. Here, we focus on the case of the Arabic language and mainly discuss the use of the G-LexAr analyzer. A preliminary experiment has been designed to choose the most promising translation system among the 3 G-LexAr-based systems, we concluded that the systems are equivalent. Nevertheless, we decided to use the lemmatized output of G-LexAr and use its translations as primary run for the BTEC AE track. The results showed that G-LexAr outputs degrades translation compared to the basic SMT system trained on the un-analyzed corpus.
%U https://aclanthology.org/2010.iwslt-evaluation.6
%P 59-65

Markdown (Informal)

[The GREYC/LLACAN machine translation systems for the IWSLT 2010 campaign](https://aclanthology.org/2010.iwslt-evaluation.6) (Gosme et al., IWSLT 2010)

• The GREYC/LLACAN machine translation systems for the IWSLT 2010 campaign (Gosme et al., IWSLT 2010)

ACL

• Julien Gosme, Wigdan Mekki, Fathi Debili, Yves Lepage, and Nadine Lucas. 2010. The GREYC/LLACAN machine translation systems for the IWSLT 2010 campaign. In Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 59–65, Paris, France.