<?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-00962386</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="2026-05-25T00:09:55+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Enhancing Patent Expertise through Automatic Matching with Scientific Papers</title>
            <author role="aut">
              <persName>
                <forename type="first">Kafil</forename>
                <surname>Hajlaoui</surname>
              </persName>
              <idno type="halauthorid">609416-0</idno>
              <affiliation ref="#struct-1814"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Pascal</forename>
                <surname>Cuxac</surname>
              </persName>
              <email type="md5">c1f7ed1e7f32959106db0ca308cd11e6</email>
              <email type="domain">inist.fr</email>
              <ptr type="url" target="https://sites.google.com/view/pascalcuxac"/>
              <idno type="idhal" notation="string">pascal-cuxac</idno>
              <idno type="idhal" notation="numeric">179348</idno>
              <idno type="halauthorid" notation="string">17089-179348</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/AAE-3002-2019</idno>
              <idno type="IDREF">https://www.idref.fr/165835257</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-6809-5654</idno>
              <idno type="VIAF">https://viaf.org/viaf/280873820</idno>
              <idno type="ISNI">http://isni.org/isni/0000000432720627</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?hl=fr&amp;user=yYY9ZqYAAAAJ</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/AAE-3002-2019</idno>
              <affiliation ref="#struct-1814"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jean-Charles</forename>
                <surname>Lamirel</surname>
              </persName>
              <email type="md5">b6dc7dc4a3589d6a60a8ff7a017b8e40</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">jean-charles-lamirel</idno>
              <idno type="idhal" notation="numeric">8202</idno>
              <idno type="halauthorid" notation="string">3050-8202</idno>
              <affiliation ref="#struct-178243"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Claire</forename>
                <surname>François</surname>
              </persName>
              <email type="md5">52a3e47889dd4767c248506cd1120f0e</email>
              <email type="domain">inist.fr</email>
              <idno type="idhal" notation="numeric">835424</idno>
              <idno type="halauthorid" notation="string">168095-835424</idno>
              <affiliation ref="#struct-1814"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Patricia</forename>
                <surname>Gautier</surname>
              </persName>
              <email type="md5">c446226da8650942ecacef7f7f918da4</email>
              <email type="domain">inist.fr</email>
            </editor>
            <funder>This work was done under the program QUAERO5 supported by OSEO6 national agency of research development.</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2014-03-21 11:10:53</date>
              <date type="whenModified">2025-11-04 11:59:06</date>
              <date type="whenReleased">2014-03-24 15:12:34</date>
              <date type="whenProduced">2012-10-29</date>
              <date type="whenEndEmbargoed">2014-03-21</date>
              <ref type="file" target="https://hal.science/hal-00962386v1/document">
                <date notBefore="2014-03-21"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-00962386v1/file/DS_paper_45.pdf" id="file-962386-604178">
                <date notBefore="2014-03-21"/>
              </ref>
              <ref type="externalLink" target="https://hal.archives-ouvertes.fr/hal-00962386/file/DS_paper_45.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="114172">
                <persName>
                  <forename>Patricia</forename>
                  <surname>Gautier</surname>
                </persName>
                <email type="md5">c446226da8650942ecacef7f7f918da4</email>
                <email type="domain">inist.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00962386</idno>
            <idno type="halUri">https://hal.science/hal-00962386</idno>
            <idno type="halBibtex">hajlaoui:hal-00962386</idno>
            <idno type="halRefHtml">&lt;i&gt;DS 2012 : The Fifteenth International Conference on Discovery Science&lt;/i&gt;, Oct 2012, Lyon, France. pp.299-312, &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-642-33492-4_24"&gt;&amp;#x27E8;10.1007/978-3-642-33492-4_24&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">DS 2012 : The Fifteenth International Conference on Discovery Science, Oct 2012, Lyon, France. pp.299-312, &amp;#x27E8;10.1007/978-3-642-33492-4_24&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-962386-604178"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
            <idno type="stamp" n="LORIA">Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
            <idno type="stamp" n="LORIA-NLPKD" corresp="LORIA">Department of Natural Language Processing &amp; Knowledge Discovery</idno>
            <idno type="stamp" n="INIST">Institut de l'Information Scientifique et Technique</idno>
            <idno type="stamp" n="PARTENARIATS-APP">Veille Partenariale Expertise et appui aux politiques publiques</idno>
            <idno type="stamp" n="INTERNE-HALCNRS">INTERNE-HALCNRS</idno>
            <idno type="stamp" n="TEST8-HALCNRS">TEST8-HALCNRS</idno>
            <idno type="stamp" n="TEST10-HALCNRS">TEST10-HALCNRS</idno>
            <idno type="stamp" n="AM2I-UL">Pôle scientifique Automatique, Mathématiques, Informatique et leurs Intéractions de l'Université de Lorraine</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">Enhancing Patent Expertise through Automatic Matching with Scientific Papers</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Kafil</forename>
                    <surname>Hajlaoui</surname>
                  </persName>
                  <idno type="halauthorid">609416-0</idno>
                  <affiliation ref="#struct-1814"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Pascal</forename>
                    <surname>Cuxac</surname>
                  </persName>
                  <email type="md5">c1f7ed1e7f32959106db0ca308cd11e6</email>
                  <email type="domain">inist.fr</email>
                  <ptr type="url" target="https://sites.google.com/view/pascalcuxac"/>
                  <idno type="idhal" notation="string">pascal-cuxac</idno>
                  <idno type="idhal" notation="numeric">179348</idno>
                  <idno type="halauthorid" notation="string">17089-179348</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/AAE-3002-2019</idno>
                  <idno type="IDREF">https://www.idref.fr/165835257</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-6809-5654</idno>
                  <idno type="VIAF">https://viaf.org/viaf/280873820</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000432720627</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?hl=fr&amp;user=yYY9ZqYAAAAJ</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/AAE-3002-2019</idno>
                  <affiliation ref="#struct-1814"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jean-Charles</forename>
                    <surname>Lamirel</surname>
                  </persName>
                  <email type="md5">b6dc7dc4a3589d6a60a8ff7a017b8e40</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">jean-charles-lamirel</idno>
                  <idno type="idhal" notation="numeric">8202</idno>
                  <idno type="halauthorid" notation="string">3050-8202</idno>
                  <affiliation ref="#struct-178243"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Claire</forename>
                    <surname>François</surname>
                  </persName>
                  <email type="md5">52a3e47889dd4767c248506cd1120f0e</email>
                  <email type="domain">inist.fr</email>
                  <idno type="idhal" notation="numeric">835424</idno>
                  <idno type="halauthorid" notation="string">168095-835424</idno>
                  <affiliation ref="#struct-1814"/>
                </author>
              </analytic>
              <monogr>
                <idno type="isbn">978-3-642-33491-7</idno>
                <title level="m">Lecture Notes in Computer Science</title>
                <meeting>
                  <title>DS 2012 : The Fifteenth International Conference on Discovery Science</title>
                  <date type="start">2012-10-29</date>
                  <date type="end">2012-10-31</date>
                  <settlement>Lyon</settlement>
                  <country key="FR">France</country>
                </meeting>
                <editor>Jean-Gabriel Ganascia</editor>
                <editor>Philippe Lenca</editor>
                <editor>Jean-Marc Petit</editor>
                <imprint>
                  <publisher>Springer</publisher>
                  <biblScope unit="serie">International Conference on Discovery Science</biblScope>
                  <biblScope unit="volume">7569</biblScope>
                  <biblScope unit="pp">299-312</biblScope>
                  <date type="datePub">2012-10-31</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-642-33492-4_24</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Patents</term>
                <term xml:lang="en">KNN</term>
                <term xml:lang="en">Association rules</term>
                <term xml:lang="en">Technological and scientific survey</term>
                <term xml:lang="en">Supervised classification</term>
                <term xml:lang="fr">Brevets</term>
                <term xml:lang="fr">Texte</term>
                <term xml:lang="fr">Classification supervisée</term>
                <term xml:lang="fr">Classification automatique</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ir">Computer Science [cs]/Information Retrieval [cs.IR]</classCode>
              <classCode scheme="halDomain" n="stat.ap">Statistics [stat]/Applications [stat.AP]</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 a subtask of the QUAERO1 research program, a major innovating research project related to the automatic processing of multimedia and multilingual content. The objective discussed in this article is to propose a new method for the classification of scientific papers, developed in the context of an international patents classification plan related to the same field. The practical purpose of this work is to provide an assistance tool to experts in their task of evaluation of the originality and novelty of a patent, by offering to the latter the most relevant scientific citations. This issue raises new challenges in categorization research as the patent classification plan is not directly adapted to the structure of scientific documents, classes have high citation or cited topic and that there is not always a balanced distribution of the available examples within the different learning classes. We propose, as a solution to this problem, to apply an improved K-nearest-neighbors (KNN) algorithm based on the exploitation of association rules occurring between the index terms of the documents and the ones of the patent classes. By using a reference dataset of patents belonging to the field of pharmacology, on the one hand, and a bibliographic dataset of the same field issued from the Medline collection, on the other hand, we show that this new approach, which combines the advantages of numerical and symbolical approaches, improves considerably categorization performance, as compared to the usual categorization methods.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1814" status="VALID">
          <idno type="IdRef">02802530X</idno>
          <idno type="ISNI">0000000089755987</idno>
          <idno type="RNSR">198822446E</idno>
          <idno type="ROR">https://ror.org/02mn0vt57</idno>
          <idno type="Wikidata">Q3152021</idno>
          <orgName>Institut de l'information scientifique et technique</orgName>
          <orgName type="acronym">INIST</orgName>
          <date type="start">1988-03-15</date>
          <desc>
            <address>
              <addrLine>2, Allée du Parc de Brabois, Rue Jean Zay, 54500 Vandœuvre-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inist.fr</ref>
          </desc>
          <listRelation>
            <relation name="UAR76 / UPS76" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-178243" status="VALID">
          <orgName>Natural Language Processing : representations, inference and semantics</orgName>
          <orgName type="acronym">SYNALP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/la-recherche-en/equipes/synalp</ref>
          </desc>
          <listRelation>
            <relation active="#struct-423086" type="direct"/>
            <relation active="#struct-206040" type="indirect"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </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="department" xml:id="struct-423086" status="VALID">
          <orgName>Department of Natural Language Processing &amp; Knowledge Discovery</orgName>
          <orgName type="acronym">LORIA - NLPKD</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/en/research/departments/natural-language-processing-and-knowledge-discovery/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-206040" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-206040" status="VALID">
          <idno type="IdRef">067077927</idno>
          <idno type="ISNI">0000000121795429</idno>
          <idno type="RNSR">198912571S</idno>
          <idno type="IdUnivLorraine">[UL]RSI--</idno>
          <idno type="ROR">https://ror.org/02vnf0c38</idno>
          <orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
          <orgName type="acronym">LORIA</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
            <relation name="UMR7503" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</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="institution" xml:id="struct-413289" status="VALID">
          <idno type="IdRef">157040569</idno>
          <idno type="IdUnivLorraine">[UL]100--</idno>
          <idno type="ROR">https://ror.org/04vfs2w97</idno>
          <orgName>Université de Lorraine</orgName>
          <orgName type="acronym">UL</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lorraine.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>