<?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-00098063</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="2026-05-16T12:09:03+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A robust linguistic infrastructure for efficient web content analysis: the ALVIS project</title>
            <author role="aut">
              <persName>
                <forename type="first">Julien</forename>
                <surname>Derivière</surname>
              </persName>
              <idno type="halauthorid">149914-0</idno>
              <affiliation ref="#struct-994"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Thierry</forename>
                <surname>Hamon</surname>
              </persName>
              <email type="md5">ed22a6c523b3033751f5788a6108904e</email>
              <email type="domain">limsi.fr</email>
              <idno type="idhal" notation="string">thierry-hamon</idno>
              <idno type="idhal" notation="numeric">11519</idno>
              <idno type="halauthorid" notation="string">32945-11519</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1521-4875</idno>
              <idno type="IDREF">https://www.idref.fr/069054711</idno>
              <idno type="VIAF">https://viaf.org/viaf/173149877</idno>
              <affiliation ref="#struct-994"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Adeline</forename>
                <surname>Nazarenko</surname>
              </persName>
              <email type="md5">18b64cbdd2f281fd08d6f8fea0eb1acd</email>
              <email type="domain">lipn.univ-paris13.fr</email>
              <idno type="idhal" notation="numeric">830553</idno>
              <idno type="halauthorid" notation="string">112144-830553</idno>
              <affiliation ref="#struct-994"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Thierry</forename>
                <surname>Poibeau</surname>
              </persName>
              <email type="md5">67d27038fe74c87b4bdafd01aec8e9df</email>
              <email type="domain">ens.fr</email>
              <idno type="idhal" notation="string">thierry-poibeau</idno>
              <idno type="idhal" notation="numeric">472</idno>
              <idno type="halauthorid" notation="string">14396-472</idno>
              <idno type="IDREF">https://www.idref.fr/069992258</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3669-4051</idno>
              <idno type="ISNI">http://isni.org/isni/0000000008826203</idno>
              <idno type="VIAF">https://viaf.org/viaf/239131</idno>
              <affiliation ref="#struct-994"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Davy</forename>
                <surname>Weissenbacher</surname>
              </persName>
              <idno type="halauthorid">149916-0</idno>
              <affiliation ref="#struct-994"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Adeline</forename>
                <surname>Nazarenko</surname>
              </persName>
              <email type="md5">18b64cbdd2f281fd08d6f8fea0eb1acd</email>
              <email type="domain">lipn.univ-paris13.fr</email>
            </editor>
            <funder>ALVIS STREP project</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2006-09-23 21:52:31</date>
              <date type="whenModified">2024-11-29 03:29:42</date>
              <date type="whenReleased">2006-09-23 21:52:31</date>
              <date type="whenProduced">2006</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="111527">
                <persName>
                  <forename>Adeline</forename>
                  <surname>Nazarenko</surname>
                </persName>
                <email type="md5">18b64cbdd2f281fd08d6f8fea0eb1acd</email>
                <email type="domain">lipn.univ-paris13.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00098063</idno>
            <idno type="halUri">https://hal.science/hal-00098063</idno>
            <idno type="halBibtex">deriviere:hal-00098063</idno>
            <idno type="halRefHtml">&lt;i&gt;Symposium on Digital Semantic Content across Cultures&lt;/i&gt;, 2006, Paris, France</idno>
            <idno type="halRef">Symposium on Digital Semantic Content across Cultures, 2006, Paris, France</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-PARIS13">Université Paris-Nord - Paris XIII </idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="OCA">Observatoire de la Cote d'Azur</idno>
            <idno type="stamp" n="LIPN" corresp="UNIV-PARIS13">Laboratoire d'Informatique de Paris-Nord</idno>
            <idno type="stamp" n="GALILE" corresp="UNIV-PARIS13">Institut Galilée Université Paris 13</idno>
            <idno type="stamp" n="SORBONNE-PARIS-NORD">Université Sorbonne Paris Nord</idno>
            <idno type="stamp" n="CONFRENCE-NATIONALE-SUR-LES-APPLICATIONS-PRATIQUES-DE-LINTELLIGENCE-ARTIFICIELLE" corresp="CNRS">Conférence Nationale sur les Applications Pratiques de l’Intelligence Artificielle </idno>
            <idno type="stamp" n="ACT-R" corresp="UNIV-PARIS13">Act'R </idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">15 pages</note>
            <note type="audience" n="1">Not set</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">A robust linguistic infrastructure for efficient web content analysis: the ALVIS project</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Julien</forename>
                    <surname>Derivière</surname>
                  </persName>
                  <idno type="halauthorid">149914-0</idno>
                  <affiliation ref="#struct-994"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Thierry</forename>
                    <surname>Hamon</surname>
                  </persName>
                  <email type="md5">ed22a6c523b3033751f5788a6108904e</email>
                  <email type="domain">limsi.fr</email>
                  <idno type="idhal" notation="string">thierry-hamon</idno>
                  <idno type="idhal" notation="numeric">11519</idno>
                  <idno type="halauthorid" notation="string">32945-11519</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1521-4875</idno>
                  <idno type="IDREF">https://www.idref.fr/069054711</idno>
                  <idno type="VIAF">https://viaf.org/viaf/173149877</idno>
                  <affiliation ref="#struct-994"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Adeline</forename>
                    <surname>Nazarenko</surname>
                  </persName>
                  <email type="md5">18b64cbdd2f281fd08d6f8fea0eb1acd</email>
                  <email type="domain">lipn.univ-paris13.fr</email>
                  <idno type="idhal" notation="numeric">830553</idno>
                  <idno type="halauthorid" notation="string">112144-830553</idno>
                  <affiliation ref="#struct-994"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Thierry</forename>
                    <surname>Poibeau</surname>
                  </persName>
                  <email type="md5">67d27038fe74c87b4bdafd01aec8e9df</email>
                  <email type="domain">ens.fr</email>
                  <idno type="idhal" notation="string">thierry-poibeau</idno>
                  <idno type="idhal" notation="numeric">472</idno>
                  <idno type="halauthorid" notation="string">14396-472</idno>
                  <idno type="IDREF">https://www.idref.fr/069992258</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3669-4051</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000008826203</idno>
                  <idno type="VIAF">https://viaf.org/viaf/239131</idno>
                  <affiliation ref="#struct-994"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Davy</forename>
                    <surname>Weissenbacher</surname>
                  </persName>
                  <idno type="halauthorid">149916-0</idno>
                  <affiliation ref="#struct-994"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Symposium on Digital Semantic Content across Cultures</title>
                  <date type="start">2006</date>
                  <settlement>Paris</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <date type="datePub">2006</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Natural language processing</term>
                <term xml:lang="en">robust text analysis</term>
                <term xml:lang="en">information retrieval</term>
                <term xml:lang="en">semantic indexing</term>
              </keywords>
              <classCode scheme="classification">H.3.1</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-ir">Computer Science [cs]/Information Retrieval [cs.IR]</classCode>
              <classCode scheme="halDomain" n="scco.comp">Cognitive science/Computer science</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 focuses on the design and the development of a text processing architecture exploiting specialized NLP tools, to produce linguistically annotated documents. This architecture is instanciated using existing NLP modules and resources which need to be tuned to specific domains. Taking as an example the biological domain, we show how a syntactic analyser can be adapted to this domain. We focus on parsing since it exhibits various kinds of adaptation, ranging from unknown words analysis to specific vocabulary (terms, named entities) and structure identification.</p>
            </abstract>
            <particDesc>
              <org type="consortium">ALVIS</org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-994" status="OLD">
          <orgName>Laboratoire d'Informatique de Paris-Nord</orgName>
          <orgName type="acronym">LIPN</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Institut Galilée, Université Paris 13, 99 avenue Jean-Baptiste Clément, F-93430, Villetaneuse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www-lipn.univ-paris13.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-15786" type="direct"/>
            <relation active="#struct-301340" type="direct"/>
            <relation active="#struct-303171" type="direct"/>
            <relation name="UMR7030" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-15786" status="VALID">
          <idno type="ROR">https://ror.org/05f82e368</idno>
          <orgName>Université Paris 13</orgName>
          <orgName type="acronym">UP13</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-paris13.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-301340" status="VALID">
          <orgName>Institut Galilée</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-303171" status="VALID">
          <idno type="IdRef">19077990X</idno>
          <idno type="ROR">https://ror.org/001z21q04</idno>
          <orgName>Université Sorbonne Paris Cité</orgName>
          <orgName type="acronym">USPC</orgName>
          <date type="start">2010-01-01</date>
          <desc>
            <address>
              <addrLine>Université Sorbonne Paris Cité | 100-104, avenue de France | 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-paris-cite.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>
      </listOrg>
    </back>
  </text>
</TEI>