<?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-00753859</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="2026-05-19T09:50:26+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Generalizing sampling-based multilingual alignment</title>
            <author role="crp">
              <persName>
                <forename type="first">Adrien</forename>
                <surname>Lardilleux</surname>
              </persName>
              <email type="md5">e55548414ddab119ecb8291e7f0aa10d</email>
              <email type="domain">info.unicaen.fr</email>
              <idno type="idhal" notation="numeric">858790</idno>
              <idno type="halauthorid" notation="string">295829-858790</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>
            <author role="aut">
              <persName>
                <forename type="first">Yves</forename>
                <surname>Lepage</surname>
              </persName>
              <email type="md5">611621ba62a385e6e3e4b890a3a0d919</email>
              <email type="domain">waseda.jp</email>
              <idno type="idhal" notation="string">yves-lepage</idno>
              <idno type="idhal" notation="numeric">1385556</idno>
              <idno type="halauthorid" notation="string">2529049-1385556</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3059-4271</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=453BsuwAAAAJ</idno>
              <affiliation ref="#struct-161013"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Adrien</forename>
                <surname>Lardilleux</surname>
              </persName>
              <email type="md5">efb20dcf5bf35e9d27e14264865f292f</email>
              <email type="domain">laposte.net</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2012-11-19 17:06:47</date>
              <date type="whenModified">2026-03-17 10:51:43</date>
              <date type="whenReleased">2012-11-19 17:06:47</date>
              <date type="whenProduced">2013-03</date>
              <ref type="externalLink" target="https://api.istex.fr/ark:/67375/VQC-RRCK4GQW-2/fulltext.pdf?sid=hal"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="138950">
                <persName>
                  <forename>Adrien</forename>
                  <surname>Lardilleux</surname>
                </persName>
                <email type="md5">efb20dcf5bf35e9d27e14264865f292f</email>
                <email type="domain">laposte.net</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00753859</idno>
            <idno type="halUri">https://hal.science/hal-00753859</idno>
            <idno type="halBibtex">lardilleux:hal-00753859</idno>
            <idno type="halRefHtml">&lt;i&gt;Machine Translation&lt;/i&gt;, 2013, 27 (1), pp.1-23. &lt;a target="_blank" href="https://dx.doi.org/10.1007/s10590-012-9126-0"&gt;&amp;#x27E8;10.1007/s10590-012-9126-0&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Machine Translation, 2013, 27 (1), pp.1-23. &amp;#x27E8;10.1007/s10590-012-9126-0&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </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="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="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Generalizing sampling-based multilingual alignment</title>
                <author role="crp">
                  <persName>
                    <forename type="first">Adrien</forename>
                    <surname>Lardilleux</surname>
                  </persName>
                  <email type="md5">e55548414ddab119ecb8291e7f0aa10d</email>
                  <email type="domain">info.unicaen.fr</email>
                  <idno type="idhal" notation="numeric">858790</idno>
                  <idno type="halauthorid" notation="string">295829-858790</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>
                <author role="aut">
                  <persName>
                    <forename type="first">Yves</forename>
                    <surname>Lepage</surname>
                  </persName>
                  <email type="md5">611621ba62a385e6e3e4b890a3a0d919</email>
                  <email type="domain">waseda.jp</email>
                  <idno type="idhal" notation="string">yves-lepage</idno>
                  <idno type="idhal" notation="numeric">1385556</idno>
                  <idno type="halauthorid" notation="string">2529049-1385556</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3059-4271</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=453BsuwAAAAJ</idno>
                  <affiliation ref="#struct-161013"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">16813</idno>
                <idno type="issn">0922-6567</idno>
                <idno type="eissn">1573-0573</idno>
                <title level="j">Machine Translation</title>
                <imprint>
                  <publisher>Springer Verlag</publisher>
                  <biblScope unit="volume">27</biblScope>
                  <biblScope unit="issue">1</biblScope>
                  <biblScope unit="pp">1-23</biblScope>
                  <date type="datePub">2013-03</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/s10590-012-9126-0</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Association measures</term>
                <term xml:lang="en">Sub-sentential alignment</term>
                <term xml:lang="en">Phrase-based machine translation</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</classCode>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Sub-sentential alignment is the process by which multi-word translation units are extracted from sentence-aligned multilingual parallel texts. This process is required, for instance, in the course of training statistical machine translation systems. Standard approaches typically rely on the estimation of several probabilistic models of increasing complexity and on the use of various heuristics, that make it possible to align, first isolated words, then, by extension, groups of words. In this paper, we explore an alternative approach which relies on a much simpler principle: the comparison of occurrence profiles in sub-corpora obtained by sampling. After analyzing the strengths and weaknesses of this approach, we show how to improve the detection of multi-word translation units and evaluate these improvements on machine translation tasks.</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="laboratory" xml:id="struct-161013" status="VALID">
          <orgName>Graduate School of Information, Production and Systems</orgName>
          <orgName type="acronym">IPS</orgName>
          <desc>
            <address>
              <addrLine>2-7 Hibikino, Wakamatsu-ku, Kitakyushu, Fukuoka 808-0135</addrLine>
              <country key="JP"/>
            </address>
            <ref type="url">http://www.waseda.jp/ips/english/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-168249" 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>
        <org type="institution" xml:id="struct-168249" status="VALID">
          <idno type="ISNI">0000 0001 2158 5974</idno>
          <orgName>Waseda University [Tokyo]</orgName>
          <desc>
            <address>
              <addrLine>1-104 Totsukamachi, Shinjuku-ku, Tokyo, 169-8050</addrLine>
              <country key="JP"/>
            </address>
            <ref type="url">https://www.waseda.jp/top/en</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>