<?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-00779799</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="2026-05-25T01:18:45+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="fr">Classification de documents combinant la structure et le contenu</title>
            <author role="aut">
              <persName>
                <forename type="first">S.</forename>
                <surname>Chagheri</surname>
              </persName>
              <idno type="halauthorid">551218-0</idno>
              <affiliation ref="#struct-394737"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Catherine</forename>
                <surname>Roussey</surname>
              </persName>
              <email type="md5">81b788da95d44a5d0cb0df278c558e2d</email>
              <email type="domain">inrae.fr</email>
              <idno type="idhal" notation="string">catherine-roussey</idno>
              <idno type="idhal" notation="numeric">185012</idno>
              <idno type="halauthorid" notation="string">49788-185012</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3076-5499</idno>
              <idno type="IDREF">https://www.idref.fr/091645638</idno>
              <orgName ref="#struct-577435"/>
              <affiliation ref="#struct-182206"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sylvie</forename>
                <surname>Calabretto</surname>
              </persName>
              <email type="md5">09a710ae99ce9de3f3bbd824b6b70d49</email>
              <email type="domain">insa-lyon.fr</email>
              <idno type="idhal" notation="string">sylvie-calabretto</idno>
              <idno type="idhal" notation="numeric">7155</idno>
              <idno type="halauthorid" notation="string">1774-7155</idno>
              <idno type="IDREF">https://www.idref.fr/061333654</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4597-4680</idno>
              <affiliation ref="#struct-394737"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">C.</forename>
                <surname>Dumoulin</surname>
              </persName>
              <idno type="halauthorid">153761-0</idno>
              <affiliation ref="#struct-212410"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Import Ws</forename>
                <surname>Irstea</surname>
              </persName>
              <email type="md5">db907169de0b78bb03b3d9d698fbf5a0</email>
              <email type="domain">irstea.fr.invalid</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2013-01-22 16:00:24</date>
              <date type="whenModified">2025-09-03 10:44:55</date>
              <date type="whenReleased">2013-01-23 15:51:00</date>
              <date type="whenProduced">2013-03-21</date>
              <date type="whenEndEmbargoed">2013-01-22</date>
              <ref type="file" target="https://hal.science/hal-00779799v1/document">
                <date notBefore="2013-01-22"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-00779799v1/file/cf2012-pub00037131.pdf" id="file-779799-727004">
                <date notBefore="2013-01-22"/>
              </ref>
              <fs>
                <f name="inra_publicVise_local" notation="string" n="SC">
                  <string>inra_publicVise_local_SC</string>
                </f>
              </fs>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="125582">
                <persName>
                  <forename>Import Ws</forename>
                  <surname>Irstea</surname>
                </persName>
                <email type="md5">db907169de0b78bb03b3d9d698fbf5a0</email>
                <email type="domain">irstea.fr.invalid</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00779799</idno>
            <idno type="halUri">https://hal.science/hal-00779799</idno>
            <idno type="halBibtex">chagheri:hal-00779799</idno>
            <idno type="halRefHtml">&lt;i&gt;8ème COnférence en Recherche d'Information et Applications CORIA 2012&lt;/i&gt;, Mar 2013, Bordeaux, France. p. 261 - p. 272</idno>
            <idno type="halRef">8ème COnférence en Recherche d'Information et Applications CORIA 2012, Mar 2013, Bordeaux, France. p. 261 - p. 272</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-779799-727004"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SDE">Sciences De l'Environnement</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-LYON1">Université Claude Bernard - Lyon I</idno>
            <idno type="stamp" n="UNIV-LYON2">Université Lumière Lyon 2</idno>
            <idno type="stamp" n="INSA-LYON">Institut National des Sciences Appliquées de Lyon</idno>
            <idno type="stamp" n="EC-LYON">Ecole Centrale de Lyon</idno>
            <idno type="stamp" n="IRSTEA">IRSTEA - Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (&lt;b&gt;anciennement Cemagref&lt;/b&gt;)</idno>
            <idno type="stamp" n="LIRIS" corresp="UNIV-LYON1">Laboratoire d'InfoRmatique en Image et Systèmes d'information</idno>
            <idno type="stamp" n="GIP-BE">GIP Bretagne Environnement</idno>
            <idno type="stamp" n="AGREENIUM">Archive ouverte en agrobiosciences</idno>
            <idno type="stamp" n="LABEXIMU">Laboratoire d’Excellence Intelligences des Mondes Urbains</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="INRAE">Institut National de Recherche en Agriculture, Alimentation et Environnement</idno>
            <idno type="stamp" n="TSCF">Unité de recherche Technologies et systèmes d'information pour les agro-systèmes</idno>
            <idno type="stamp" n="MATHNUM">Département MathNum</idno>
            <idno type="stamp" n="TEST-MATHNUM">Test MathNum</idno>
            <idno type="stamp" n="HAL-LYON-2-NOUVELLE-VERSION">Nouvelle version portail </idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">[Departement_IRSTEA]Ecotechnologies [TR1_IRSTEA]MOTIVE</note>
            <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">Classification de documents combinant la structure et le contenu</title>
                <author role="aut">
                  <persName>
                    <forename type="first">S.</forename>
                    <surname>Chagheri</surname>
                  </persName>
                  <idno type="halauthorid">551218-0</idno>
                  <affiliation ref="#struct-394737"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Catherine</forename>
                    <surname>Roussey</surname>
                  </persName>
                  <email type="md5">81b788da95d44a5d0cb0df278c558e2d</email>
                  <email type="domain">inrae.fr</email>
                  <idno type="idhal" notation="string">catherine-roussey</idno>
                  <idno type="idhal" notation="numeric">185012</idno>
                  <idno type="halauthorid" notation="string">49788-185012</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3076-5499</idno>
                  <idno type="IDREF">https://www.idref.fr/091645638</idno>
                  <orgName ref="#struct-577435"/>
                  <affiliation ref="#struct-182206"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sylvie</forename>
                    <surname>Calabretto</surname>
                  </persName>
                  <email type="md5">09a710ae99ce9de3f3bbd824b6b70d49</email>
                  <email type="domain">insa-lyon.fr</email>
                  <idno type="idhal" notation="string">sylvie-calabretto</idno>
                  <idno type="idhal" notation="numeric">7155</idno>
                  <idno type="halauthorid" notation="string">1774-7155</idno>
                  <idno type="IDREF">https://www.idref.fr/061333654</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4597-4680</idno>
                  <affiliation ref="#struct-394737"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">C.</forename>
                    <surname>Dumoulin</surname>
                  </persName>
                  <idno type="halauthorid">153761-0</idno>
                  <affiliation ref="#struct-212410"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>8ème COnférence en Recherche d'Information et Applications CORIA 2012</title>
                  <date type="start">2013-03-21</date>
                  <date type="end">2012-03-23</date>
                  <settlement>Bordeaux</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">p. 261 - p. 272</biblScope>
                  <date type="datePub">2012</date>
                </imprint>
              </monogr>
              <idno type="irstea">PUB00037131</idno>
              <ref target="http://asso-aria.org/coria/2012/261.pdf" type="seeAlso"/>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="fr">MODELE VECTORIEL</term>
                <term xml:lang="fr">REPRESENTATION DES CONNAISSANCES</term>
                <term xml:lang="fr">MACHINE A VECTEURS DE SUPPORT</term>
                <term xml:lang="fr">TF-IEF</term>
                <term xml:lang="fr">LANGAGE XML</term>
                <term xml:lang="fr">REPRESENTATION DE DOCUMENT</term>
                <term xml:lang="fr">CLASSIFICATION SUPERVISEE</term>
                <term xml:lang="fr">TF-IDF</term>
                <term xml:lang="fr">DOCUMENT STRUCTURE</term>
              </keywords>
              <classCode scheme="halDomain" n="sde">Environmental Sciences</classCode>
              <classCode scheme="vocinrae-old" n="EXTENSIBLE MARKUP LANGUAGE">EXTENSIBLE MARKUP LANGUAGE</classCode>
              <classCode scheme="vocinrae-old" n="MACHINE A VECTEURS DE SUPPORT">MACHINE A VECTEURS DE SUPPORT</classCode>
              <classCode scheme="vocinrae-old" n="REPRESENTATION DES CONNAISSANCES">REPRESENTATION DES CONNAISSANCES</classCode>
              <classCode scheme="vocinrae-old" n="LANGAGE XML">LANGAGE XML</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>La démocratisation et l’évolution des logiciels de traitements de texte ont révolutionné le monde du document. Les auteurs construisent des documents dits structurés c'est-à-dire dont le contenu textuel s’organise autours de balises. Toutefois, la classification traditionnelle de documents n’utilise que le contenu textuel des documents et ignore les informations de structure. Dans ce papier, nous proposons une nouvelle représentation des documents structurés basée sur un vecteur pondéré associant un mot et une balise. Les poids sont calculés en adaptant les formules TF-IDF et TF-IEF. Cette représentation est construite à partir d’une représentation synthétique du document appelé arbre résumé. Pour évaluer notre approche, nous avons mené plusieurs expérimentations avec un système de classification basé sur le classifieur SVMlight. Nous présentons les résultats de nos expérimentations menées sur les corpus REUTERS et INEX. / Developing the text processing applications has revolutionized the world of documents. The author constructs the document as structured document in which the textual content is organized around tags. However, the traditional document classification typically classifies the documents considering the text and ignoring its structural elements. In this paper, we propose a representation method which makes use of structural elements to create the vector of tag and word weighted by an extension of TF-IDF and TF-IEF formula. This representation is constructed from an aggregated tree of XML document. Several experimentations have been made using SVMlight as classifier on Reuters and INEX collections.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-394737" status="VALID">
          <orgName>Distribution, Recherche d'Information et Mobilité</orgName>
          <orgName type="acronym">DRIM</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-2003" type="direct"/>
            <relation active="#struct-33804" type="indirect"/>
            <relation active="#struct-126765" type="indirect"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="indirect"/>
            <relation active="#struct-219748" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-182206" status="OLD">
          <idno type="RNSR">200118619N</idno>
          <orgName>Technologies et systèmes d'information pour les agrosystèmes</orgName>
          <orgName type="acronym">UR TSCF</orgName>
          <date type="start">2012-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>9 avenue Blaise Pascal CS 20085 F-63178 Aubière ; Domaine des Palaquins, F-03150 Montoldre</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irstea.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UR1471" active="#struct-302049" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-212410" status="INCOMING">
          <orgName>aucun</orgName>
          <desc>
            <address>
              <addrLine>Roanne</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-338482" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2003" status="VALID">
          <idno type="IdRef">149705271</idno>
          <idno type="ISNI">0000000122577669</idno>
          <idno type="RNSR">200511875R</idno>
          <idno type="ROR">https://ror.org/04dv4he91</idno>
          <orgName>Laboratoire d'InfoRmatique en Image et Systèmes d'information</orgName>
          <orgName type="acronym">LIRIS</orgName>
          <date type="start">2003-01-01</date>
          <desc>
            <address>
              <addrLine>Bâtiment Blaise Pascal - 20, avenue Albert Einstein - 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://liris.cnrs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-33804" type="direct"/>
            <relation active="#struct-126765" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="direct"/>
            <relation active="#struct-219748" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-33804" status="VALID">
          <idno type="IdRef">02640334X</idno>
          <idno type="ISNI">0000 0001 2188 0906</idno>
          <idno type="ROR">https://ror.org/03rth4p18</idno>
          <idno type="Wikidata">Q4041</idno>
          <orgName>Université Lumière - Lyon 2</orgName>
          <orgName type="acronym">UL2</orgName>
          <desc>
            <address>
              <addrLine>86, rue Pasteur - 69007 Lyon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon2.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-126765" status="VALID">
          <idno type="ROR">https://ror.org/05s6rge65</idno>
          <orgName>École Centrale de Lyon</orgName>
          <orgName type="acronym">ECL</orgName>
          <desc>
            <address>
              <addrLine>36 avenue Guy de Collongue - 69134 Ecully cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ec-lyon.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301088" status="VALID">
          <idno type="ROR">https://ror.org/01rk35k63</idno>
          <orgName>Université de Lyon</orgName>
          <desc>
            <address>
              <addrLine>92 rue Pasteur - CS 30122, 69361 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-lyon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-194495" status="VALID">
          <idno type="IdRef">026402823</idno>
          <idno type="ISNI">0000000121686185</idno>
          <idno type="ROR">https://ror.org/029brtt94</idno>
          <orgName>Université Claude Bernard Lyon 1</orgName>
          <orgName type="acronym">UCBL</orgName>
          <desc>
            <address>
              <addrLine>43, boulevard du 11 novembre 1918, 69622 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-219748" status="VALID">
          <idno type="IdRef">052444724</idno>
          <idno type="ISNI">0000 0001 2292 0228</idno>
          <orgName>Institut National des Sciences Appliquées de Lyon</orgName>
          <orgName type="acronym">INSA Lyon</orgName>
          <date type="start">1957-03-18</date>
          <desc>
            <address>
              <addrLine>20 Avenue Albert Einstein, 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-lyon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
            <relation active="#struct-301232" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </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-302049" status="OLD">
          <idno type="ROR">https://ror.org/01wep6g48</idno>
          <orgName>Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture</orgName>
          <orgName type="acronym">IRSTEA</orgName>
          <date type="start">2012-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irstea.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-338482" status="INCOMING">
          <orgName>Continew</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>