<?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-02949042</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="2026-05-25T13:01:27+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Generative latent neural models for automatic word alignment</title>
            <author role="aut">
              <persName>
                <forename type="first">Anh Khoa</forename>
                <surname>Ngo Ho</surname>
              </persName>
              <email type="md5">8d1378d8c01105be769304557f9e2629</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">anh-khoa-ngo-ho</idno>
              <idno type="idhal" notation="numeric">744016</idno>
              <idno type="halauthorid" notation="string">51225-744016</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4844-5012</idno>
              <idno type="IDREF">https://www.idref.fr/255027419</idno>
              <affiliation ref="#struct-1041999"/>
            </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-1041999"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Anh Khoa</forename>
                <surname>NGO HO</surname>
              </persName>
              <email type="md5">8d1378d8c01105be769304557f9e2629</email>
              <email type="domain">gmail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-09-25 12:07:17</date>
              <date type="whenModified">2025-05-05 17:46:30</date>
              <date type="whenReleased">2020-09-28 09:54:28</date>
              <date type="whenProduced">2020-10-06</date>
              <date type="whenEndEmbargoed">2020-09-25</date>
              <ref type="file" target="https://hal.science/hal-02949042v1/document">
                <date notBefore="2020-09-25"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02949042v1/file/amta2020.pdf" id="file-2949042-2596620">
                <date notBefore="2020-09-25"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="643786">
                <persName>
                  <forename>Anh Khoa</forename>
                  <surname>NGO HO</surname>
                </persName>
                <email type="md5">8d1378d8c01105be769304557f9e2629</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02949042</idno>
            <idno type="halUri">https://hal.science/hal-02949042</idno>
            <idno type="halBibtex">ngoho:hal-02949042</idno>
            <idno type="halRefHtml">&lt;i&gt;The Association for Machine Translation in the Americas&lt;/i&gt;, Oct 2020, Florida, United States. pp.64-77</idno>
            <idno type="halRef">The Association for Machine Translation in the Americas, Oct 2020, Florida, United States. pp.64-77</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2949042-2596620"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</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="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="LISN">Laboratoire Interdisciplinaire des Sciences du Numérique</idno>
            <idno type="stamp" n="GS-ENGINEERING">Graduate School Sciences de l'Ingénierie et des Systèmes</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="LISN-TLP" corresp="LISN">Traitement du Langage Parlé </idno>
            <idno type="stamp" n="LISN-STL">Sciences et Technologies des Langues</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">Generative latent neural models for automatic word alignment</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Anh Khoa</forename>
                    <surname>Ngo Ho</surname>
                  </persName>
                  <email type="md5">8d1378d8c01105be769304557f9e2629</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">anh-khoa-ngo-ho</idno>
                  <idno type="idhal" notation="numeric">744016</idno>
                  <idno type="halauthorid" notation="string">51225-744016</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4844-5012</idno>
                  <idno type="IDREF">https://www.idref.fr/255027419</idno>
                  <affiliation ref="#struct-1041999"/>
                </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-1041999"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>The Association for Machine Translation in the Americas</title>
                  <date type="start">2020-10-06</date>
                  <date type="end">2020-10-09</date>
                  <settlement>Florida</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint>
                  <biblScope unit="serie">Proceedings of the 14th Conference of the Association for Machine Translation in the Americas</biblScope>
                  <biblScope unit="volume">Volume 1: Research Track</biblScope>
                  <biblScope unit="pp">64–77</biblScope>
                  <date type="datePub">2020-10-09</date>
                </imprint>
              </monogr>
              <ref type="publisher">https://amtaweb.org/amta-2020-conference-program-and-registration-are-available/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</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>Word alignments identify translational correspondences between words in a parallel sentence pair and are used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems or to perform quality estimation. Variational autoencoders have been recently used in various of natural language processing to learn in an unsupervised way latent representations that are useful for language generation tasks. In this paper, we study these models for the task of word alignment and propose and assess several evolutions of a vanilla variational autoencoders. We demonstrate that these techniques can yield competitive results as compared to Giza++ and to a strong neural network alignment system for two language pairs.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1041999" status="OLD">
          <orgName>Traitement du Langage Parlé</orgName>
          <orgName type="acronym">TLP</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2020-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 508, 91405, Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.limsi.fr/fr/recherche/tlp</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1041968" type="direct"/>
            <relation active="#struct-419361" type="indirect"/>
            <relation name="UPR3251" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1041968" status="OLD">
          <orgName>Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur</orgName>
          <orgName type="acronym">LIMSI</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2020-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 507, rue du Belvédère,91405, Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.limsi.fr/fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UPR3251" active="#struct-441569" type="direct"/>
          </listRelation>
        </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>
      </listOrg>
    </back>
  </text>
</TEI>