<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-01908381</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-17T18:31:59+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A fully discriminative training framework for Statistical Machine Translation</title>
            <title xml:lang="fr">Un cadre d'apprentissage intégralement discriminant pour la traduction statistique</title>
            <author role="aut">
              <persName>
                <forename type="first">Thomas</forename>
                <surname>Lavergne</surname>
              </persName>
              <email type="md5">4537e847a61faa1382bde6c5fa528d54</email>
              <email type="domain">limsi.fr</email>
              <idno type="idhal" notation="string">lavergne-thomas</idno>
              <idno type="idhal" notation="numeric">1296801</idno>
              <idno type="halauthorid" notation="string">513652-1296801</idno>
              <idno type="IDREF">https://www.idref.fr/197749852</idno>
              <idno type="ORCID">https://orcid.org/0009-0009-0338-4648</idno>
              <idno type="VIAF">https://viaf.org/viaf/410148704251536931413</idno>
              <affiliation ref="#struct-247329"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Alexandre</forename>
                <surname>Allauzen</surname>
              </persName>
              <email type="md5">0124166ad70f06a6272745c1e04cfb46</email>
              <email type="domain">dauphine.psl.eu</email>
              <idno type="idhal" notation="string">alexandre-allauzen</idno>
              <idno type="idhal" notation="numeric">171266</idno>
              <idno type="halauthorid" notation="string">13659-171266</idno>
              <idno type="IDREF">https://www.idref.fr/078187621</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-8627-1965</idno>
              <idno type="VIAF">https://viaf.org/viaf/218292984</idno>
              <idno type="ISNI">http://isni.org/isni/0000000140297249</idno>
              <affiliation ref="#struct-247329"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">François</forename>
                <surname>Yvon</surname>
              </persName>
              <email type="md5">c62025aca0c6cf8d65b4fe9600c991af</email>
              <email type="domain">cnrs.fr</email>
              <idno type="idhal" notation="string">francois-yvon</idno>
              <idno type="idhal" notation="numeric">5347</idno>
              <idno type="halauthorid" notation="string">2529017-5347</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7972-7442</idno>
              <idno type="IDREF">https://www.idref.fr/057593531</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=JjfDvawAAAAJ</idno>
              <idno type="ARXIV">https://arxiv.org/a/yvon_f_1</idno>
              <affiliation ref="#struct-247329"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Limsi</forename>
                <surname>Publications</surname>
              </persName>
              <email type="md5">8e5605f65b0cc7a415570f9c535b6d01</email>
              <email type="domain">limsi.fr</email>
            </editor>
            <funder>Ce travail a été partiellement financé par OSEO dans le cadre du programme Quaero.</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-12-16 17:02:28</date>
              <date type="whenWritten">2013</date>
              <date type="whenModified">2026-02-14 10:46:58</date>
              <date type="whenReleased">2022-12-16 17:28:54</date>
              <date type="whenProduced">2013-06-17</date>
              <date type="whenEndEmbargoed">2022-12-16</date>
              <ref type="file" target="https://hal.science/hal-01908381v1/document">
                <date notBefore="2022-12-16"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-01908381v1/file/perdu.pdf" id="file-3904003-3414104">
                <date notBefore="2022-12-16"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="560720">
                <persName>
                  <forename>Limsi</forename>
                  <surname>Publications</surname>
                </persName>
                <email type="md5">8e5605f65b0cc7a415570f9c535b6d01</email>
                <email type="domain">limsi.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01908381</idno>
            <idno type="halUri">https://hal.science/hal-01908381</idno>
            <idno type="halBibtex">lavergne:hal-01908381</idno>
            <idno type="halRefHtml">&lt;i&gt;20ème Conférence sur le Traitement Automatique des Langues Naturelles&lt;/i&gt;, Jun 2013, Batz-les-Bains, France</idno>
            <idno type="halRef">20ème Conférence sur le Traitement Automatique des Langues Naturelles, Jun 2013, Batz-les-Bains, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3904003-3414104"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-PSUD">Université Paris Sud - Paris XI</idno>
            <idno type="stamp" n="LIMSI">Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIV-PSUD-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris Sud pour Paris Saclay</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SU-INF-2018" corresp="SORBONNE-UNIVERSITE">SORBONNE université &lt;2018</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="LISN">Laboratoire Interdisciplinaire des Sciences du Numérique</idno>
            <idno type="stamp" n="GS-SPORT-HUMAN-MOVEMENT">Graduate School Sport, Mouvement, Facteurs Humains</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="1">Not set</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">A fully discriminative training framework for Statistical Machine Translation</title>
                <title xml:lang="fr">Un cadre d'apprentissage intégralement discriminant pour la traduction statistique</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Thomas</forename>
                    <surname>Lavergne</surname>
                  </persName>
                  <email type="md5">4537e847a61faa1382bde6c5fa528d54</email>
                  <email type="domain">limsi.fr</email>
                  <idno type="idhal" notation="string">lavergne-thomas</idno>
                  <idno type="idhal" notation="numeric">1296801</idno>
                  <idno type="halauthorid" notation="string">513652-1296801</idno>
                  <idno type="IDREF">https://www.idref.fr/197749852</idno>
                  <idno type="ORCID">https://orcid.org/0009-0009-0338-4648</idno>
                  <idno type="VIAF">https://viaf.org/viaf/410148704251536931413</idno>
                  <affiliation ref="#struct-247329"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Alexandre</forename>
                    <surname>Allauzen</surname>
                  </persName>
                  <email type="md5">0124166ad70f06a6272745c1e04cfb46</email>
                  <email type="domain">dauphine.psl.eu</email>
                  <idno type="idhal" notation="string">alexandre-allauzen</idno>
                  <idno type="idhal" notation="numeric">171266</idno>
                  <idno type="halauthorid" notation="string">13659-171266</idno>
                  <idno type="IDREF">https://www.idref.fr/078187621</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-8627-1965</idno>
                  <idno type="VIAF">https://viaf.org/viaf/218292984</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000140297249</idno>
                  <affiliation ref="#struct-247329"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">François</forename>
                    <surname>Yvon</surname>
                  </persName>
                  <email type="md5">c62025aca0c6cf8d65b4fe9600c991af</email>
                  <email type="domain">cnrs.fr</email>
                  <idno type="idhal" notation="string">francois-yvon</idno>
                  <idno type="idhal" notation="numeric">5347</idno>
                  <idno type="halauthorid" notation="string">2529017-5347</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7972-7442</idno>
                  <idno type="IDREF">https://www.idref.fr/057593531</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=JjfDvawAAAAJ</idno>
                  <idno type="ARXIV">https://arxiv.org/a/yvon_f_1</idno>
                  <affiliation ref="#struct-247329"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>20ème Conférence sur le Traitement Automatique des Langues Naturelles</title>
                  <date type="start">2013-06-17</date>
                  <date type="end">2013-06-21</date>
                  <settlement>Batz-les-Bains</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
              <ref type="publisher">https://www.atala.org/content/taln-recital-2013-20%C3%A8me-conf%C3%A9rence-sur-le-traitement-automatique-des-langues-naturelles</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Machine Translation</term>
                <term xml:lang="en">Discriminative Learning</term>
                <term xml:lang="fr">Apprentissage Discriminant</term>
                <term xml:lang="fr">Traduction Automatique</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>A major pitfall of existing statistical machine translation systems is their lack of a proper training procedure. In fact, the phrase extraction and scoring processes that underlie the construction of the translation model typically rely on a chain of crude heuristics, a situation deemed problematic by many. In this paper, we recast machine translation in the familiar terms of a probabilistic structure learning problem, using a standard log-linear parameterization. The tractability of this enterprise is achieved through an efficient implementation that can take into account all the aspects of the underlying translation process through latent variables. We also address the reference reachability issue by using oracle decoding techniques. This approach is experimentally contrasted with a state-of-the-art system on the French-English BTEC translation task.</p>
            </abstract>
            <abstract xml:lang="fr">
              <p>Une faiblesse des systèmes de traduction statistiques est le caractère ad hoc du processus d'apprentissage, qui repose sur un empilement d'heuristiques et conduit à apprendre des paramètres dont la valeur est sous-optimale. Dans ce travail, nous reformulons la traduction automatique sous la forme familière de l'apprentissage d'un modèle probabiliste structuré utilisant une paramérisation log-linéaire. Cette entreprise est rendue possible par le développement d'une implantation efficace qui permet en particulier de prendre en compte la présence de variables latentes dans le modèle. Notre approche est comparée, avec succès, avec une approche de l'état de l'art sur la tâche de traduction de données du BTEC pour le couple Français-Anglais.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-247329" status="OLD">
          <orgName>Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur</orgName>
          <orgName type="acronym">LIMSI</orgName>
          <date type="start">1962-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Université Paris-Sud Bât. 507 - Rue du Belvédère -91405 ORSAY CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.limsi.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92966" type="direct"/>
            <relation active="#struct-408837" type="direct"/>
            <relation active="#struct-413221" type="indirect"/>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UPR3251" active="#struct-441569" type="direct"/>
            <relation active="#struct-562112" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-92966" status="OLD">
          <idno type="ROR">https://ror.org/028rypz17</idno>
          <orgName>Université Paris-Sud - Paris 11</orgName>
          <orgName type="acronym">UP11</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 300 - 91405 Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-psud.fr/</ref>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-408837" status="VALID">
          <orgName>Sorbonne Université - UFR d'Ingénierie</orgName>
          <orgName type="acronym">UFR 919</orgName>
          <desc>
            <address>
              <addrLine>SORBONNE UNIVERSITEFACULTE DES SCIENCES ET INGENIERIEUFR D'INGENIERIETour 55/65 - 2e étage4 place Jussieu75252 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ingenierie.sorbonne-universite.fr/fr/index.html</ref>
          </desc>
          <listRelation>
            <relation active="#struct-413221" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-413221" status="VALID">
          <idno type="IdRef">221333754</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Sorbonne Université</orgName>
          <orgName type="acronym">SU</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>21 rue de l’École de médecine - 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-universite.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-419361" status="VALID">
          <idno type="IdRef">241345251</idno>
          <idno type="ROR">https://ror.org/03xjwb503</idno>
          <orgName>Université Paris-Saclay</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Bréguet, 3 Rue Joliot Curie 2e ét, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/fr</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</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"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-562112" status="OLD">
          <orgName>Université Paris Saclay (COmUE)</orgName>
          <desc>
            <address>
              <addrLine>Espace Technologique, Bât. Discovery - RD 128 - 2è ététage, 91190 Saint-Aubin</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/fr</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>