Training Statistical Machine Translation with Multivariate Mutual Information
Identifieur interne : 004F38 ( Hal/Corpus ); précédent : 004F37; suivant : 004F39Training Statistical Machine Translation with Multivariate Mutual Information
Auteurs : Cyrine Nasri ; Kamel Smaili ; Chiraz LatiriSource :
English descriptors
Abstract
In this paper, we describe a new model for phrase-based statistical machine translation. Roughly speaking, statistical approach uses a language and a translation model. This latter could be viewed as a lexical and an alignment model. The approach we propose does not need any alignment, it is based on inter-lingual triggers determined by multivariate mutual information (MMI). This measure depends on conditional mutual information, this means that a source phrase is directly linked to a target one. The conditional mutual information is used in both directions (source-target and target-source languages). We present an experimental evaluation conducted on EUROPARL corpora (French and English) and using the decoder MOSES. We compare then our results to those of a previous work in which we used inter-lingual triggers determined by a simple mutual information (MI) as well as to those given by baseline model (Koehn et al., 2003).
Url:
Links to Exploration step
Hal:hal-01272104Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Training Statistical Machine Translation with Multivariate Mutual Information</title>
<author><name sortKey="Nasri, Cyrine" sort="Nasri, Cyrine" uniqKey="Nasri C" first="Cyrine" last="Nasri">Cyrine Nasri</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-407170" status="VALID"><orgName>Statistical Machine Translation and Speech Modelization and Text </orgName>
<orgName type="acronym">SMarT</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche/equipes/smart</ref>
</desc>
<listRelation><relation active="#struct-423086" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-423086" type="direct"><org type="department" xml:id="struct-423086" status="VALID"><orgName>Department of Natural Language Processing & Knowledge Discovery</orgName>
<orgName type="acronym">LORIA - NLPKD</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/Knowledge-and-Language-Management</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
<orgName type="acronym">Inria</orgName>
<desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/en/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</org>
</tutelle>
<tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno>
<idno type="ISNI">0000000122597504</idno>
<orgName>Centre National de la Recherche Scientifique</orgName>
<orgName type="acronym">CNRS</orgName>
<date type="start">1939-10-19</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.cnrs.fr/</ref>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
<author><name sortKey="Smaili, Kamel" sort="Smaili, Kamel" uniqKey="Smaili K" first="Kamel" last="Smaili">Kamel Smaili</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-407170" status="VALID"><orgName>Statistical Machine Translation and Speech Modelization and Text </orgName>
<orgName type="acronym">SMarT</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche/equipes/smart</ref>
</desc>
<listRelation><relation active="#struct-423086" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-423086" type="direct"><org type="department" xml:id="struct-423086" status="VALID"><orgName>Department of Natural Language Processing & Knowledge Discovery</orgName>
<orgName type="acronym">LORIA - NLPKD</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/Knowledge-and-Language-Management</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
<orgName type="acronym">Inria</orgName>
<desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/en/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</org>
</tutelle>
<tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno>
<idno type="ISNI">0000000122597504</idno>
<orgName>Centre National de la Recherche Scientifique</orgName>
<orgName type="acronym">CNRS</orgName>
<date type="start">1939-10-19</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.cnrs.fr/</ref>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
<author><name sortKey="Latiri, Chiraz" sort="Latiri, Chiraz" uniqKey="Latiri C" first="Chiraz" last="Latiri">Chiraz Latiri</name>
<affiliation><hal:affiliation type="institution" xml:id="struct-302442" status="VALID"><orgName>Université de Tunis - El Manar</orgName>
<desc><address><country key="TN"></country>
</address>
</desc>
</hal:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">HAL</idno>
<idno type="RBID">Hal:hal-01272104</idno>
<idno type="halId">hal-01272104</idno>
<idno type="halUri">https://hal.archives-ouvertes.fr/hal-01272104</idno>
<idno type="url">https://hal.archives-ouvertes.fr/hal-01272104</idno>
<date when="2011-11-27">2011-11-27</date>
<idno type="wicri:Area/Hal/Corpus">004F38</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Training Statistical Machine Translation with Multivariate Mutual Information</title>
<author><name sortKey="Nasri, Cyrine" sort="Nasri, Cyrine" uniqKey="Nasri C" first="Cyrine" last="Nasri">Cyrine Nasri</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-407170" status="VALID"><orgName>Statistical Machine Translation and Speech Modelization and Text </orgName>
<orgName type="acronym">SMarT</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche/equipes/smart</ref>
</desc>
<listRelation><relation active="#struct-423086" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-423086" type="direct"><org type="department" xml:id="struct-423086" status="VALID"><orgName>Department of Natural Language Processing & Knowledge Discovery</orgName>
<orgName type="acronym">LORIA - NLPKD</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/Knowledge-and-Language-Management</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
<orgName type="acronym">Inria</orgName>
<desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/en/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</org>
</tutelle>
<tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno>
<idno type="ISNI">0000000122597504</idno>
<orgName>Centre National de la Recherche Scientifique</orgName>
<orgName type="acronym">CNRS</orgName>
<date type="start">1939-10-19</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.cnrs.fr/</ref>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
<author><name sortKey="Smaili, Kamel" sort="Smaili, Kamel" uniqKey="Smaili K" first="Kamel" last="Smaili">Kamel Smaili</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-407170" status="VALID"><orgName>Statistical Machine Translation and Speech Modelization and Text </orgName>
<orgName type="acronym">SMarT</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche/equipes/smart</ref>
</desc>
<listRelation><relation active="#struct-423086" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-423086" type="direct"><org type="department" xml:id="struct-423086" status="VALID"><orgName>Department of Natural Language Processing & Knowledge Discovery</orgName>
<orgName type="acronym">LORIA - NLPKD</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/Knowledge-and-Language-Management</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
<orgName type="acronym">Inria</orgName>
<desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/en/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</org>
</tutelle>
<tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno>
<idno type="ISNI">0000000122597504</idno>
<orgName>Centre National de la Recherche Scientifique</orgName>
<orgName type="acronym">CNRS</orgName>
<date type="start">1939-10-19</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.cnrs.fr/</ref>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
<author><name sortKey="Latiri, Chiraz" sort="Latiri, Chiraz" uniqKey="Latiri C" first="Chiraz" last="Latiri">Chiraz Latiri</name>
<affiliation><hal:affiliation type="institution" xml:id="struct-302442" status="VALID"><orgName>Université de Tunis - El Manar</orgName>
<desc><address><country key="TN"></country>
</address>
</desc>
</hal:affiliation>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="mix" xml:lang="en"><term>BLEU</term>
<term>Conditionnal Mutual Information</term>
<term>Machine translation</term>
<term>Phrases</term>
<term>inter-lingual triggers</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">In this paper, we describe a new model for phrase-based statistical machine translation. Roughly speaking, statistical approach uses a language and a translation model. This latter could be viewed as a lexical and an alignment model. The approach we propose does not need any alignment, it is based on inter-lingual triggers determined by multivariate mutual information (MMI). This measure depends on conditional mutual information, this means that a source phrase is directly linked to a target one. The conditional mutual information is used in both directions (source-target and target-source languages). We present an experimental evaluation conducted on EUROPARL corpora (French and English) and using the decoder MOSES. We compare then our results to those of a previous work in which we used inter-lingual triggers determined by a simple mutual information (MI) as well as to those given by baseline model (Koehn et al., 2003).</div>
</front>
</TEI>
<hal api="V3"><titleStmt><title xml:lang="en">Training Statistical Machine Translation with Multivariate Mutual Information</title>
<author role="aut"><persName><forename type="first">Cyrine</forename>
<surname>Nasri</surname>
</persName>
<email>cyrine.nasri@loria.fr</email>
<idno type="halauthor">1291921</idno>
<orgName ref="#struct-446629"></orgName>
<affiliation ref="#struct-407170"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Kamel</forename>
<surname>Smaili</surname>
</persName>
<email>smaili@loria.fr</email>
<idno type="halauthor">1291922</idno>
<affiliation ref="#struct-407170"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Chiraz</forename>
<surname>Latiri</surname>
</persName>
<email>chiraz.latiri@gnet.tn</email>
<idno type="halauthor">756783</idno>
<affiliation ref="#struct-302442"></affiliation>
</author>
<editor role="depositor"><persName><forename>Kamel</forename>
<surname>Smaïli</surname>
</persName>
<email>smaili@loria.fr</email>
</editor>
</titleStmt>
<editionStmt><edition n="v1" type="current"><date type="whenSubmitted">2016-02-10 11:08:01</date>
<date type="whenModified">2016-02-12 01:08:07</date>
<date type="whenReleased">2016-02-11 10:32:20</date>
<date type="whenProduced">2011-11-27</date>
<date type="whenEndEmbargoed">2016-02-10</date>
<ref type="file" target="https://hal.archives-ouvertes.fr/hal-01272104/document"><date notBefore="2016-02-10"></date>
</ref>
<ref type="file" subtype="author" n="1" target="https://hal.archives-ouvertes.fr/hal-01272104/file/LTC2011NasriSmailiLatiri.pdf"><date notBefore="2016-02-10"></date>
</ref>
</edition>
<respStmt><resp>contributor</resp>
<name key="103558"><persName><forename>Kamel</forename>
<surname>Smaïli</surname>
</persName>
<email>smaili@loria.fr</email>
</name>
</respStmt>
</editionStmt>
<publicationStmt><distributor>CCSD</distributor>
<idno type="halId">hal-01272104</idno>
<idno type="halUri">https://hal.archives-ouvertes.fr/hal-01272104</idno>
<idno type="halBibtex">nasri:hal-01272104</idno>
<idno type="halRefHtml">5th Language and Technology Conference, Nov 2011, Poznan, Poland</idno>
<idno type="halRef">5th Language and Technology Conference, Nov 2011, Poznan, Poland</idno>
</publicationStmt>
<seriesStmt><idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
<idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
<idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
<idno type="stamp" n="LORIA2">Publications du LORIA</idno>
</seriesStmt>
<notesStmt><note type="audience" n="2">International</note>
<note type="invited" n="0">No</note>
<note type="popular" n="0">No</note>
<note type="peer" n="1">Yes</note>
<note type="proceedings" n="0">No</note>
</notesStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Training Statistical Machine Translation with Multivariate Mutual Information</title>
<author role="aut"><persName><forename type="first">Cyrine</forename>
<surname>Nasri</surname>
</persName>
<email>cyrine.nasri@loria.fr</email>
<idno type="halAuthorId">1291921</idno>
<orgName ref="#struct-446629"></orgName>
<affiliation ref="#struct-407170"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Kamel</forename>
<surname>Smaili</surname>
</persName>
<email>smaili@loria.fr</email>
<idno type="halAuthorId">1291922</idno>
<affiliation ref="#struct-407170"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Chiraz</forename>
<surname>Latiri</surname>
</persName>
<email>chiraz.latiri@gnet.tn</email>
<idno type="halAuthorId">756783</idno>
<affiliation ref="#struct-302442"></affiliation>
</author>
</analytic>
<monogr><meeting><title>5th Language and Technology Conference</title>
<date type="start">2011-11-27</date>
<date type="end">2011-11-29</date>
<settlement>Poznan</settlement>
<country key="PL">Poland</country>
</meeting>
<imprint></imprint>
</monogr>
</biblStruct>
</sourceDesc>
<profileDesc><langUsage><language ident="en">English</language>
</langUsage>
<textClass><keywords scheme="author"><term xml:lang="en">Phrases</term>
<term xml:lang="en">Machine translation</term>
<term xml:lang="en">inter-lingual triggers</term>
<term xml:lang="en">Conditionnal Mutual Information</term>
<term xml:lang="en">BLEU</term>
</keywords>
<classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</classCode>
<classCode scheme="halTypology" n="COMM">Conference papers</classCode>
</textClass>
<abstract xml:lang="en">In this paper, we describe a new model for phrase-based statistical machine translation. Roughly speaking, statistical approach uses a language and a translation model. This latter could be viewed as a lexical and an alignment model. The approach we propose does not need any alignment, it is based on inter-lingual triggers determined by multivariate mutual information (MMI). This measure depends on conditional mutual information, this means that a source phrase is directly linked to a target one. The conditional mutual information is used in both directions (source-target and target-source languages). We present an experimental evaluation conducted on EUROPARL corpora (French and English) and using the decoder MOSES. We compare then our results to those of a previous work in which we used inter-lingual triggers determined by a simple mutual information (MI) as well as to those given by baseline model (Koehn et al., 2003).</abstract>
</profileDesc>
</hal>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Hal/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 004F38 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Hal/Corpus/biblio.hfd -nk 004F38 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Hal |étape= Corpus |type= RBID |clé= Hal:hal-01272104 |texte= Training Statistical Machine Translation with Multivariate Mutual Information }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |