<?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-00293255</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="2026-05-18T07:22:31+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Contextual and Metadata-based Approach for the Semantic Annotation of Heterogeneous Documents</title>
            <author role="aut">
              <persName>
                <forename type="first">Mouhamadou</forename>
                <surname>Thiam</surname>
              </persName>
              <idno type="halauthorid">293148-0</idno>
              <affiliation ref="#struct-21400"/>
              <affiliation ref="#struct-2544"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nathalie</forename>
                <surname>Pernelle</surname>
              </persName>
              <email type="md5">d4056480a0e0bb2e140ea8a7c698079f</email>
              <email type="domain">lri.fr</email>
              <idno type="idhal" notation="string">nathalie-pernelle</idno>
              <idno type="idhal" notation="numeric">16213</idno>
              <idno type="halauthorid" notation="string">6232-16213</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1487-393X</idno>
              <idno type="IDREF">https://www.idref.fr/124298095</idno>
              <affiliation ref="#struct-2544"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nacéra</forename>
                <surname>Bennacer Seghouani</surname>
              </persName>
              <email type="md5">7177b5266ea2e94f7f3d243a30dc4f7a</email>
              <email type="domain">lisn.fr</email>
              <idno type="idhal" notation="string">bennacer</idno>
              <idno type="idhal" notation="numeric">5306</idno>
              <idno type="halauthorid" notation="string">6078-5306</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7320-0316</idno>
              <idno type="IDREF">https://www.idref.fr/140470409</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=dfFhbokAAAAJ</idno>
              <affiliation ref="#struct-21400"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Evelyne</forename>
                <surname>Faivre</surname>
              </persName>
              <email type="md5">36664f1be53870a1bda189ab2af6508c</email>
              <email type="domain">supelec.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2009-12-11 16:18:27</date>
              <date type="whenModified">2024-02-10 03:07:45</date>
              <date type="whenReleased">2009-12-14 11:26:17</date>
              <date type="whenProduced">2008-06-01</date>
              <date type="whenEndEmbargoed">2009-12-11</date>
              <ref type="file" target="https://centralesupelec.hal.science/hal-00293255v1/document">
                <date notBefore="2009-12-11"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://centralesupelec.hal.science/hal-00293255v1/file/PapierSemma.pdf" id="file-293255-472581">
                <date notBefore="2009-12-11"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="123536">
                <persName>
                  <forename>Evelyne</forename>
                  <surname>Faivre</surname>
                </persName>
                <email type="md5">36664f1be53870a1bda189ab2af6508c</email>
                <email type="domain">supelec.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00293255</idno>
            <idno type="halUri">https://centralesupelec.hal.science/hal-00293255</idno>
            <idno type="halBibtex">thiam:hal-00293255</idno>
            <idno type="halRefHtml">&lt;i&gt;1st Workshop on Semantic Metadata Management and Applications (SeMMA 2008) at the 5 th European Semantic Web Conference (ESWC 2008)&lt;/i&gt;, Jun 2008, Tenerife, Spain. pp.16-28</idno>
            <idno type="halRef">1st Workshop on Semantic Metadata Management and Applications (SeMMA 2008) at the 5 th European Semantic Web Conference (ESWC 2008), Jun 2008, Tenerife, Spain. pp.16-28</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-293255-472581"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SUPELEC">SUPELEC</idno>
            <idno type="stamp" n="EC-PARIS">Ecole Centrale Paris</idno>
            <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="UMR8623">Laboratoire de Recherche en Informatique</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</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>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">ISSN 1613-0073</note>
            <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">Contextual and Metadata-based Approach for the Semantic Annotation of Heterogeneous Documents</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Mouhamadou</forename>
                    <surname>Thiam</surname>
                  </persName>
                  <idno type="halauthorid">293148-0</idno>
                  <affiliation ref="#struct-21400"/>
                  <affiliation ref="#struct-2544"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nathalie</forename>
                    <surname>Pernelle</surname>
                  </persName>
                  <email type="md5">d4056480a0e0bb2e140ea8a7c698079f</email>
                  <email type="domain">lri.fr</email>
                  <idno type="idhal" notation="string">nathalie-pernelle</idno>
                  <idno type="idhal" notation="numeric">16213</idno>
                  <idno type="halauthorid" notation="string">6232-16213</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1487-393X</idno>
                  <idno type="IDREF">https://www.idref.fr/124298095</idno>
                  <affiliation ref="#struct-2544"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nacéra</forename>
                    <surname>Bennacer Seghouani</surname>
                  </persName>
                  <email type="md5">7177b5266ea2e94f7f3d243a30dc4f7a</email>
                  <email type="domain">lisn.fr</email>
                  <idno type="idhal" notation="string">bennacer</idno>
                  <idno type="idhal" notation="numeric">5306</idno>
                  <idno type="halauthorid" notation="string">6078-5306</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7320-0316</idno>
                  <idno type="IDREF">https://www.idref.fr/140470409</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=dfFhbokAAAAJ</idno>
                  <affiliation ref="#struct-21400"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of the 1st Workshop on Semantic Metadata Management and Applications (SeMMA 2008) at the 5 th European Semantic Web Conference (ESWC 2008)</title>
                <meeting>
                  <title>1st Workshop on Semantic Metadata Management and Applications (SeMMA 2008) at the 5 th European Semantic Web Conference (ESWC 2008)</title>
                  <date type="start">2008-06-01</date>
                  <settlement>Tenerife</settlement>
                  <country key="ES">Spain</country>
                </meeting>
                <imprint>
                  <biblScope unit="volume">346</biblScope>
                  <biblScope unit="pp">16-28</biblScope>
                  <date type="datePub">2008</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Semantic Annotation</term>
                <term xml:lang="en">Metadata</term>
                <term xml:lang="en">Ontology</term>
                <term xml:lang="en">HTML</term>
                <term xml:lang="en">RDF/RDFS</term>
                <term xml:lang="en">Logical rules</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-wb">Computer Science [cs]/Web</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>In this paper, we present SHIRI-Annot, an automatic ontology- driven and unsupervised approach for the semantic annotation of doc- uments which contain more or less structured parts. The aim of this approach is to build an integration system called SHIRI 3 which allows the user access to documents related to a specific domain. In this sys- tem, the querying process is guided by an ontology of the domain and the answers are only made of the pertinent parts of the documents unlike keywords-based search engines. The ontology is described using RDFS (Resource Description Framework Schema) language. The SHIRI-Annot approach consists of locating and then annotating concept instances and their semantic relations. The locating step combines existing annotation approaches in order to locate instances in the text. The annotation step exploits a set of metadata and a set of logical rule patterns which are automatically instanciated from the domain description. These metadata are provided from the ontology or are defined specifically for the annota- tion task. The resulting annotations are represented in RDF (Resource Description Framework) language. We show through a preliminary study made on a corpus of HTML documents the usefulness of these specific metadata to represent the heterogeneity of documents. We also illus- trate through examples how the SHIRI system exploits the metadata to approximate the user queries in order to provide more pertinent answers.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-21400" status="OLD">
          <orgName>SUPELEC-Campus Gif</orgName>
          <desc>
            <address>
              <addrLine>Plateau du Moulon - 3 rue Joliot-Curie - 91192 Gif-sur-Yvette CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.supelec.fr/gif/</ref>
          </desc>
          <listRelation>
            <relation name="300812" active="#struct-303397" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2544" status="OLD">
          <idno type="RNSR">199812948M</idno>
          <orgName>Laboratoire de Recherche en Informatique</orgName>
          <orgName type="acronym">LRI</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>LRI - Bâtiments 650-660 Université Paris-Sud 91405 Orsay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lri.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92966" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation name="UMR8623" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-303397" status="VALID">
          <orgName>Ecole Supérieure d'Electricité - SUPELEC (FRANCE)</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </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="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.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>