<?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-02550811</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="2026-05-17T21:14:26+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">SIMTEX: An Approach for Detecting and Measuring Textual Similarity based on Discourse and Semantics</title>
            <author role="aut">
              <persName>
                <forename type="first">Iria</forename>
                <surname>da Cunha</surname>
              </persName>
              <idno type="halauthorid">1025371-0</idno>
              <affiliation ref="#struct-128785"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jorge</forename>
                <surname>Vivaldi</surname>
              </persName>
              <idno type="halauthorid">1027551-0</idno>
              <affiliation ref="#struct-128785"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Juan-Manuel</forename>
                <surname>Torres-Moreno</surname>
              </persName>
              <email type="md5">24e01ff455b854be4517b4ba9d593cf2</email>
              <email type="domain">univ-avignon.fr</email>
              <idno type="idhal" notation="string">juan-manuel-torres</idno>
              <idno type="idhal" notation="numeric">12610</idno>
              <idno type="halauthorid" notation="string">8811-12610</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4392-1825</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=NtQBItYAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/130897019</idno>
              <affiliation ref="#struct-100376"/>
              <affiliation ref="#struct-57241"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gerardo Eugenio</forename>
                <surname>Sierra-Martinez</surname>
              </persName>
              <idno type="halauthorid">1025372-0</idno>
              <affiliation ref="#struct-250023"/>
              <affiliation ref="#struct-100376"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Juan-Manuel</forename>
                <surname>TORRES-MORENO</surname>
              </persName>
              <email type="md5">24e01ff455b854be4517b4ba9d593cf2</email>
              <email type="domain">univ-avignon.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-05-04 17:32:31</date>
              <date type="whenModified">2022-08-08 17:38:05</date>
              <date type="whenReleased">2020-05-07 14:21:47</date>
              <date type="whenProduced">2014-09-30</date>
              <date type="whenEndEmbargoed">2020-04-22</date>
              <ref type="file" target="https://hal.science/hal-02550811v1/document">
                <date notBefore="2020-04-22"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-02550811v1/file/SIMTEX_An_Approach_for_Detecting_and_Mea.pdf" id="file-2550827-2432079">
                <date notBefore="2020-04-22"/>
              </ref>
              <ref type="externalLink" target="http://pdfs.semanticscholar.org/62cd/972639417bc218b67329bb7031a6e30c9c64.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="22873">
                <persName>
                  <forename>Juan-Manuel</forename>
                  <surname>TORRES-MORENO</surname>
                </persName>
                <email type="md5">24e01ff455b854be4517b4ba9d593cf2</email>
                <email type="domain">univ-avignon.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02550811</idno>
            <idno type="halUri">https://hal.science/hal-02550811</idno>
            <idno type="halBibtex">dacunha:hal-02550811</idno>
            <idno type="halRefHtml">&lt;i&gt;Computación y sistemas&lt;/i&gt;, 2014, 18 (3), &lt;a target="_blank" href="https://dx.doi.org/10.13053/CyS-18-3-2033"&gt;&amp;#x27E8;10.13053/CyS-18-3-2033&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Computación y sistemas, 2014, 18 (3), &amp;#x27E8;10.13053/CyS-18-3-2033&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2550827-2432079"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-AVIGNON">Université d'Avignon</idno>
            <idno type="stamp" n="LIA" corresp="UNIV-AVIGNON">Laboratoire Informatique d'Avignon</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">SIMTEX: An Approach for Detecting and Measuring Textual Similarity based on Discourse and Semantics</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Iria</forename>
                    <surname>da Cunha</surname>
                  </persName>
                  <idno type="halauthorid">1025371-0</idno>
                  <affiliation ref="#struct-128785"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jorge</forename>
                    <surname>Vivaldi</surname>
                  </persName>
                  <idno type="halauthorid">1027551-0</idno>
                  <affiliation ref="#struct-128785"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Juan-Manuel</forename>
                    <surname>Torres-Moreno</surname>
                  </persName>
                  <email type="md5">24e01ff455b854be4517b4ba9d593cf2</email>
                  <email type="domain">univ-avignon.fr</email>
                  <idno type="idhal" notation="string">juan-manuel-torres</idno>
                  <idno type="idhal" notation="numeric">12610</idno>
                  <idno type="halauthorid" notation="string">8811-12610</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4392-1825</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=NtQBItYAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/130897019</idno>
                  <affiliation ref="#struct-100376"/>
                  <affiliation ref="#struct-57241"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gerardo Eugenio</forename>
                    <surname>Sierra-Martinez</surname>
                  </persName>
                  <idno type="halauthorid">1025372-0</idno>
                  <affiliation ref="#struct-250023"/>
                  <affiliation ref="#struct-100376"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">108578</idno>
                <idno type="issn">1405-5546</idno>
                <idno type="eissn">2007-9737</idno>
                <title level="j">Computación y sistemas</title>
                <imprint>
                  <publisher> Instituto Politécnico Nacional IPN Centro de Investigación en Computación</publisher>
                  <biblScope unit="volume">18</biblScope>
                  <biblScope unit="issue">3</biblScope>
                  <date type="datePub">2014-09-30</date>
                </imprint>
              </monogr>
              <idno type="doi">10.13053/CyS-18-3-2033</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Textual similarity</term>
                <term xml:lang="en">semantics</term>
                <term xml:lang="en">paraphrase</term>
                <term xml:lang="en">discourse</term>
              </keywords>
              <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="info.info-tt">Computer Science [cs]/Document and Text Processing</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Nowadays automatic systems for detecting and measuring textual similarity are being developed, in order to apply them to different tasks in the field of Natural Language Processing (NLP). Currently, these systems use surface linguistic features or statistical information. Nowadays, few researchers use deep linguistic information. In this work, we present an algorithm for detecting and measuring textual similarity that takes into account information offered by discourse relations of Rhetorical Structure Theory (RST), and lexical-semantic relations included in EuroWordNet. We apply the algorithm , called SIMTEX, to texts written in Spanish, but the methodology is potentially language-independent.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="regroupinstitution" xml:id="struct-128785" status="VALID">
          <idno type="ROR">https://ror.org/04n0g0b29</idno>
          <orgName>Universitat Pompeu Fabra [Barcelona]</orgName>
          <orgName type="acronym">UPF</orgName>
          <desc>
            <address>
              <addrLine>Plaça de la Mercè, 10-12 - 08002 Barcelona</addrLine>
              <country key="ES"/>
            </address>
            <ref type="url">https://www.upf.edu/en/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-100376" status="VALID">
          <orgName>Laboratoire Informatique d'Avignon</orgName>
          <orgName type="acronym">LIA</orgName>
          <desc>
            <address>
              <addrLine>339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://lia.univ-avignon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-195507" type="direct"/>
            <relation active="#struct-302221" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-57241" status="VALID">
          <idno type="ROR">https://ror.org/05f8d4e86</idno>
          <orgName>École Polytechnique de Montréal</orgName>
          <orgName type="acronym">EPM</orgName>
          <desc>
            <address>
              <addrLine>Campus de l'Université de Montréal - 2500, chemin de Polytechnique - Montréal (Québec) H3T 1J4</addrLine>
              <country key="CA"/>
            </address>
            <ref type="url">http://www.polymtl.ca/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-250023" status="VALID">
          <orgName>Universidad Nacional Autónoma de México = National Autonomous University of Mexico</orgName>
          <orgName type="acronym">UNAM</orgName>
          <desc>
            <address>
              <addrLine>Av. Universidad 3004, Col, Copilco Universidad, Coyoacán, 04510 Ciudad de México,</addrLine>
              <country key="MX"/>
            </address>
            <ref type="url">https://www.unam.mx/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-195507" status="VALID">
          <idno type="ROR">https://ror.org/00mfpxb84</idno>
          <orgName>Avignon Université</orgName>
          <orgName type="acronym">AU</orgName>
          <desc>
            <address>
              <addrLine>74 rue Louis Pasteur - 84 029 Avignon cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-avignon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-302221" status="VALID">
          <orgName>Centre d'Enseignement et de Recherche en Informatique - CERI</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>