<?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-00577127</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="2026-05-17T06:51:17+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Automatic Web Pages Author Extraction</title>
            <author role="aut">
              <persName>
                <forename type="first">Sahar</forename>
                <surname>Changuel</surname>
              </persName>
              <email type="md5">e43cd0b1770720cbb494e92af66d1d68</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">895674</idno>
              <idno type="halauthorid" notation="string">544375-895674</idno>
              <affiliation ref="#struct-396897"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nicolas</forename>
                <surname>Labroche</surname>
              </persName>
              <email type="md5">47763ec1a694c4768ea29814586eab79</email>
              <email type="domain">univ-tours.fr</email>
              <idno type="idhal" notation="string">nicolas-labroche</idno>
              <idno type="idhal" notation="numeric">4509</idno>
              <idno type="halauthorid" notation="string">8396-4509</idno>
              <idno type="IDREF">https://www.idref.fr/132080303</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2794-2124</idno>
              <affiliation ref="#struct-396897"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Bernadette</forename>
                <surname>Bouchon-Meunier</surname>
              </persName>
              <email type="md5">362012f1edb8493cf2159e7534a59ba7</email>
              <email type="domain">lip6.fr</email>
              <idno type="idhal" notation="string">bernadette-bouchon-meunier</idno>
              <idno type="idhal" notation="numeric">9708</idno>
              <idno type="halauthorid" notation="string">9616-9708</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7937-7796</idno>
              <idno type="IDREF">https://www.idref.fr/031064442</idno>
              <affiliation ref="#struct-396897"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Sahar</forename>
                <surname>Changuel</surname>
              </persName>
              <email type="md5">e43cd0b1770720cbb494e92af66d1d68</email>
              <email type="domain">gmail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2011-03-16 13:30:12</date>
              <date type="whenWritten">2009</date>
              <date type="whenModified">2023-04-11 15:16:28</date>
              <date type="whenReleased">2011-03-16 13:30:12</date>
              <date type="whenProduced">2009-10</date>
              <ref type="externalLink" target="https://api.istex.fr/ark:/67375/HCB-3WQDPBSS-9/fulltext.pdf?sid=hal"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="160278">
                <persName>
                  <forename>Sahar</forename>
                  <surname>Changuel</surname>
                </persName>
                <email type="md5">e43cd0b1770720cbb494e92af66d1d68</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00577127</idno>
            <idno type="halUri">https://hal.science/hal-00577127</idno>
            <idno type="halBibtex">changuel:hal-00577127</idno>
            <idno type="halRefHtml">&lt;i&gt;FQAS 2009 - 8th International Conference on Flexible Query Answering Systems&lt;/i&gt;, Oct 2009, Roskilde, Denmark. pp.300-311, &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-642-04957-6_26"&gt;&amp;#x27E8;10.1007/978-3-642-04957-6_26&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">FQAS 2009 - 8th International Conference on Flexible Query Answering Systems, Oct 2009, Roskilde, Denmark. pp.300-311, &amp;#x27E8;10.1007/978-3-642-04957-6_26&amp;#x27E9;</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>
            <idno type="stamp" n="TEST3-HALCNRS">TEST3-HALCNRS</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="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Automatic Web Pages Author Extraction</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Sahar</forename>
                    <surname>Changuel</surname>
                  </persName>
                  <email type="md5">e43cd0b1770720cbb494e92af66d1d68</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">895674</idno>
                  <idno type="halauthorid" notation="string">544375-895674</idno>
                  <affiliation ref="#struct-396897"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nicolas</forename>
                    <surname>Labroche</surname>
                  </persName>
                  <email type="md5">47763ec1a694c4768ea29814586eab79</email>
                  <email type="domain">univ-tours.fr</email>
                  <idno type="idhal" notation="string">nicolas-labroche</idno>
                  <idno type="idhal" notation="numeric">4509</idno>
                  <idno type="halauthorid" notation="string">8396-4509</idno>
                  <idno type="IDREF">https://www.idref.fr/132080303</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2794-2124</idno>
                  <affiliation ref="#struct-396897"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Bernadette</forename>
                    <surname>Bouchon-Meunier</surname>
                  </persName>
                  <email type="md5">362012f1edb8493cf2159e7534a59ba7</email>
                  <email type="domain">lip6.fr</email>
                  <idno type="idhal" notation="string">bernadette-bouchon-meunier</idno>
                  <idno type="idhal" notation="numeric">9708</idno>
                  <idno type="halauthorid" notation="string">9616-9708</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7937-7796</idno>
                  <idno type="IDREF">https://www.idref.fr/031064442</idno>
                  <affiliation ref="#struct-396897"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>FQAS 2009 - 8th International Conference on Flexible Query Answering Systems</title>
                  <date type="start">2009-10</date>
                  <settlement>Roskilde</settlement>
                  <country key="DK">Denmark</country>
                </meeting>
                <imprint>
                  <publisher>Springer</publisher>
                  <biblScope unit="serie">Lecture Notes in Computer Science</biblScope>
                  <biblScope unit="volume">5822</biblScope>
                  <biblScope unit="pp">300-311</biblScope>
                  <date type="datePub">2009</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-642-04957-6_26</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <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>This paper addresses the problem of automatically extracting the author from heterogeneous HTML resources as a sub problem of automatic metadata extraction from (Web) documents. We take a supervised machine learning approach to address the problem using a C4.5 Decision Tree algorithm. The particularity of our approach is that it focuses on both, structure and contextual information. A semi-automatic approach was conducted for corpus expansion in order to help annotating the dataset with less human effort. This paper shows that our method can achieve good results (more than 80% in term of F1-measure) despite the heterogeneity of our corpus.</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>