<?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-01352081</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="2026-05-21T17:45:13+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="fr">Modèle probabiliste pour l'extraction de structures dans les documents semi-structurés: Application aux documents Web</title>
            <author role="aut">
              <persName>
                <forename type="first">Guillaume</forename>
                <surname>Wisniewski</surname>
              </persName>
              <email type="md5">267e8ab6f6a30a7f9012995e72c36696</email>
              <email type="domain">u-paris.fr</email>
              <idno type="idhal" notation="string">guillaume-wisniewski</idno>
              <idno type="idhal" notation="numeric">748468</idno>
              <idno type="halauthorid" notation="string">13660-748468</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=knVG9GIAAAAJ&amp;hl=fr&amp;oi=ao</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=knVG9GIAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/128062290</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4445-080X</idno>
              <affiliation ref="#struct-396897"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ludovic</forename>
                <surname>Denoyer</surname>
              </persName>
              <email type="md5">5a966f98d3670909f62ad2f0e0a0ec3f</email>
              <email type="domain">lip6.fr</email>
              <idno type="idhal" notation="string">ludovic-denoyer</idno>
              <idno type="idhal" notation="numeric">9178</idno>
              <idno type="halauthorid" notation="string">5171-9178</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7348-788X</idno>
              <idno type="IDREF">https://www.idref.fr/089291255</idno>
              <orgName ref="#struct-93591"/>
              <affiliation ref="#struct-396897"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Francis</forename>
                <surname>Maes</surname>
              </persName>
              <email type="md5">dc7c59cad7498238867597cb8b8d2e89</email>
              <email type="domain">lip6.fr</email>
              <idno type="idhal" notation="numeric">968152</idno>
              <idno type="halauthorid" notation="string">862497-968152</idno>
              <affiliation ref="#struct-396897"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Patrick</forename>
                <surname>Gallinari</surname>
              </persName>
              <email type="md5">d928d788b4143b63dbc87c6175a152be</email>
              <email type="domain">sorbonne-universite.fr</email>
              <idno type="idhal" notation="string">patrick-gallinari</idno>
              <idno type="idhal" notation="numeric">751615</idno>
              <idno type="halauthorid" notation="string">1778-751615</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-9060-9001</idno>
              <idno type="IDREF">https://www.idref.fr/070709076</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/CSF-2807-2022</idno>
              <idno type="VIAF">https://viaf.org/viaf/6686337</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/CSF-2807-2022</idno>
              <affiliation ref="#struct-396897"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Lip6</forename>
                <surname>Publications</surname>
              </persName>
              <email type="md5">48f930374cf1d03f2eafeaae16bb5814</email>
              <email type="domain">lip6.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2016-08-05 14:30:33</date>
              <date type="whenModified">2025-08-20 03:23:07</date>
              <date type="whenReleased">2016-08-05 14:30:33</date>
              <date type="whenProduced">2006-03</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="196566">
                <persName>
                  <forename>Lip6</forename>
                  <surname>Publications</surname>
                </persName>
                <email type="md5">48f930374cf1d03f2eafeaae16bb5814</email>
                <email type="domain">lip6.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01352081</idno>
            <idno type="halUri">https://hal.science/hal-01352081</idno>
            <idno type="halBibtex">wisniewski:hal-01352081</idno>
            <idno type="halRefHtml">&lt;i&gt;3eme Conference en Recherche d'Information et Applications (CORIA'06)&lt;/i&gt;, Mar 2006, Lyon, France. pp.169-180</idno>
            <idno type="halRef">3eme Conference en Recherche d'Information et Applications (CORIA'06), Mar 2006, Lyon, France. pp.169-180</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UPMC" corresp="SORBONNE-UNIVERSITE">Université Pierre et Marie Curie</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="LIP6" corresp="SORBONNE-UNIVERSITE">Laboratoire d'Informatique de Paris 6</idno>
            <idno type="stamp" n="UPMC_POLE_1" corresp="UPMC">UPMC Pôle 1</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="3">National</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="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="fr">Modèle probabiliste pour l'extraction de structures dans les documents semi-structurés: Application aux documents Web</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Guillaume</forename>
                    <surname>Wisniewski</surname>
                  </persName>
                  <email type="md5">267e8ab6f6a30a7f9012995e72c36696</email>
                  <email type="domain">u-paris.fr</email>
                  <idno type="idhal" notation="string">guillaume-wisniewski</idno>
                  <idno type="idhal" notation="numeric">748468</idno>
                  <idno type="halauthorid" notation="string">13660-748468</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=knVG9GIAAAAJ&amp;hl=fr&amp;oi=ao</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=knVG9GIAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/128062290</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4445-080X</idno>
                  <affiliation ref="#struct-396897"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ludovic</forename>
                    <surname>Denoyer</surname>
                  </persName>
                  <email type="md5">5a966f98d3670909f62ad2f0e0a0ec3f</email>
                  <email type="domain">lip6.fr</email>
                  <idno type="idhal" notation="string">ludovic-denoyer</idno>
                  <idno type="idhal" notation="numeric">9178</idno>
                  <idno type="halauthorid" notation="string">5171-9178</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7348-788X</idno>
                  <idno type="IDREF">https://www.idref.fr/089291255</idno>
                  <orgName ref="#struct-93591"/>
                  <affiliation ref="#struct-396897"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Francis</forename>
                    <surname>Maes</surname>
                  </persName>
                  <email type="md5">dc7c59cad7498238867597cb8b8d2e89</email>
                  <email type="domain">lip6.fr</email>
                  <idno type="idhal" notation="numeric">968152</idno>
                  <idno type="halauthorid" notation="string">862497-968152</idno>
                  <affiliation ref="#struct-396897"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Patrick</forename>
                    <surname>Gallinari</surname>
                  </persName>
                  <email type="md5">d928d788b4143b63dbc87c6175a152be</email>
                  <email type="domain">sorbonne-universite.fr</email>
                  <idno type="idhal" notation="string">patrick-gallinari</idno>
                  <idno type="idhal" notation="numeric">751615</idno>
                  <idno type="halauthorid" notation="string">1778-751615</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-9060-9001</idno>
                  <idno type="IDREF">https://www.idref.fr/070709076</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/CSF-2807-2022</idno>
                  <idno type="VIAF">https://viaf.org/viaf/6686337</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/CSF-2807-2022</idno>
                  <affiliation ref="#struct-396897"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">3eme Conference en Recherche d'Information et Applications (CORIA'06)</title>
                <meeting>
                  <title>3eme Conference en Recherche d'Information et Applications (CORIA'06)</title>
                  <date type="start">2006-03</date>
                  <settlement>Lyon</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">169-180</biblScope>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</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="fr">
              <p>Le développement des systèmes de gestion de contenu a profondément changé la nature du Web : de plus en plus de documents sont créés automatiquement et leur mise en page reflète leur structure logique. Dans ce travail, nous montrons que l’information contenue dans la mise en page est suffisante pour inférer une structure sémantiquement riche, ce qui ouvre la voie à de nombreuses applications. Le passage d’une information de mise en page à une structure sémantique se heurte à deux principaux obstacles : l’hétérogénéité des données et le caractère implicite de de la structure des documents Web. Nous décrivons un modèle stochastique capable d’apprendre à transformer des documents semi-structurés vers un schéma défini a priori et présentons une instance particulière de ce modèle adaptée à la transformation de documents hétérogènes HTML en XML. Finalement, nous décrivons plusieurs expériences sur des corpus XML et HTML réels.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-396897" status="OLD">
          <orgName>Machine Learning and Information Retrieval</orgName>
          <orgName type="acronym">MALIRE</orgName>
          <date type="start">2004-01-01</date>
          <date type="end">2012-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-233" type="direct"/>
            <relation active="#struct-93591" type="indirect"/>
            <relation name="UMR7606" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-233" status="OLD">
          <idno type="RNSR">199712651U</idno>
          <idno type="ROR">https://ror.org/05krcen59</idno>
          <orgName>Laboratoire d'Informatique de Paris 6</orgName>
          <orgName type="acronym">LIP6</orgName>
          <date type="start">1997-01-01</date>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>4 Place JUSSIEU 75252 PARIS CEDEX 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lip6.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-93591" type="direct"/>
            <relation name="UMR7606" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-93591" status="OLD">
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Université Pierre et Marie Curie - Paris 6</orgName>
          <orgName type="acronym">UPMC</orgName>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>4 place Jussieu - 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.upmc.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>