<?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 cea-01857881</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="2026-05-24T22:23:54+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="fr">Désambiguïsation d’entités nommées par apprentissage de modèles d’entités à large échelle</title>
            <author role="aut">
              <persName>
                <forename type="first">Hani</forename>
                <surname>Daher</surname>
              </persName>
              <email type="md5">d4af608e55cc9064f1a8541c9cd9d745</email>
              <email type="domain">cea.fr</email>
              <idno type="idhal" notation="numeric">1035641</idno>
              <idno type="halauthorid" notation="string">488633-1035641</idno>
              <affiliation ref="#struct-241319"/>
              <affiliation ref="#struct-184143"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Romaric</forename>
                <surname>Besançon</surname>
              </persName>
              <email type="md5">b00b48722a03ec84ab174917a6d4ebd6</email>
              <email type="domain">cea.fr</email>
              <idno type="idhal" notation="string">romaric-besancon</idno>
              <idno type="idhal" notation="numeric">1072760</idno>
              <idno type="halauthorid" notation="string">1411074-1072760</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1331-5768</idno>
              <affiliation ref="#struct-241319"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Olivier</forename>
                <surname>Ferret</surname>
              </persName>
              <email type="md5">383cec00a00425ccdb255ad20191a98e</email>
              <email type="domain">cea.fr</email>
              <idno type="idhal" notation="string">olivier-ferret</idno>
              <idno type="idhal" notation="numeric">14770</idno>
              <idno type="halauthorid" notation="string">22591-14770</idno>
              <idno type="IDREF">https://www.idref.fr/155894498</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0755-2361</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=-mCQhtIAAAAJ</idno>
              <idno type="ARXIV">https://arxiv.org/a/ferret_o_1</idno>
              <affiliation ref="#struct-241319"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hervé</forename>
                <surname>Le Borgne</surname>
              </persName>
              <email type="md5">56ea649a249c59b0f72edac99322c287</email>
              <email type="domain">cea.fr</email>
              <idno type="idhal" notation="string">herve-le-borgne</idno>
              <idno type="idhal" notation="numeric">181478</idno>
              <idno type="halauthorid" notation="string">1029-181478</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0520-8436</idno>
              <idno type="IDREF">https://www.idref.fr/079208452</idno>
              <affiliation ref="#struct-241319"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Anne-Laure</forename>
                <surname>Daquo</surname>
              </persName>
              <email type="md5">a8894d87c9a7f441330dab9bdcddf01c</email>
              <email type="domain">cea.fr</email>
              <idno type="idhal" notation="numeric">1035642</idno>
              <idno type="halauthorid" notation="string">1411075-1035642</idno>
              <affiliation ref="#struct-241319"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Youssef</forename>
                <surname>Tamaazousti</surname>
              </persName>
              <idno type="halauthorid">1374829-0</idno>
              <affiliation ref="#struct-241319"/>
              <affiliation ref="#struct-435635"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Olivier</forename>
                <surname>Ferret</surname>
              </persName>
              <email type="md5">383cec00a00425ccdb255ad20191a98e</email>
              <email type="domain">cea.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2018-08-17 15:30:58</date>
              <date type="whenModified">2024-09-03 11:16:05</date>
              <date type="whenReleased">2018-08-18 21:21:25</date>
              <date type="whenProduced">2017</date>
              <date type="whenEndEmbargoed">2018-08-17</date>
              <ref type="file" target="https://cea.hal.science/cea-01857881v1/document">
                <date notBefore="2018-08-17"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://cea.hal.science/cea-01857881v1/file/23.pdf" id="file-1857881-1884675">
                <date notBefore="2018-08-17"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="119831">
                <persName>
                  <forename>Olivier</forename>
                  <surname>Ferret</surname>
                </persName>
                <email type="md5">383cec00a00425ccdb255ad20191a98e</email>
                <email type="domain">cea.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">cea-01857881</idno>
            <idno type="halUri">https://cea.hal.science/cea-01857881</idno>
            <idno type="halBibtex">daher:cea-01857881</idno>
            <idno type="halRefHtml">&lt;i&gt;14ème COnférence en Recherche d'Information et Applications (CORIA 2017)&lt;/i&gt;, 2017, Marseille, France. pp.185-200</idno>
            <idno type="halRef">14ème COnférence en Recherche d'Information et Applications (CORIA 2017), 2017, Marseille, France. pp.185-200</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1857881-1884675"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CEA">CEA - Commissariat à l'énergie atomique</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="DRT" corresp="CEA">Direction de la recherche technologique</idno>
            <idno type="stamp" n="MICS">Mathématiques et Informatique pour la Complexité et les Systèmes</idno>
            <idno type="stamp" n="CEA-UPSAY" corresp="CEA">CEA - Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="CEA-UPSAY-SACLAY" corresp="CEA">CEA-UPSAY-SACLAY</idno>
            <idno type="stamp" n="CENTRALESUPELEC-SACLAY" corresp="UNIV-PARIS-SACLAY">CENTRALESUPELEC-SACLAY</idno>
            <idno type="stamp" n="LIST" corresp="CEA">Laboratoire d'Intégration des Systèmes et des Technologies</idno>
            <idno type="stamp" n="GS-ENGINEERING">Graduate School Sciences de l'Ingénierie et des Systèmes</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="GS-SPORT-HUMAN-MOVEMENT">Graduate School Sport, Mouvement, Facteurs Humains</idno>
          </seriesStmt>
          <notesStmt>
            <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">Désambiguïsation d’entités nommées par apprentissage de modèles d’entités à large échelle</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Hani</forename>
                    <surname>Daher</surname>
                  </persName>
                  <email type="md5">d4af608e55cc9064f1a8541c9cd9d745</email>
                  <email type="domain">cea.fr</email>
                  <idno type="idhal" notation="numeric">1035641</idno>
                  <idno type="halauthorid" notation="string">488633-1035641</idno>
                  <affiliation ref="#struct-241319"/>
                  <affiliation ref="#struct-184143"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Romaric</forename>
                    <surname>Besançon</surname>
                  </persName>
                  <email type="md5">b00b48722a03ec84ab174917a6d4ebd6</email>
                  <email type="domain">cea.fr</email>
                  <idno type="idhal" notation="string">romaric-besancon</idno>
                  <idno type="idhal" notation="numeric">1072760</idno>
                  <idno type="halauthorid" notation="string">1411074-1072760</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1331-5768</idno>
                  <affiliation ref="#struct-241319"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Olivier</forename>
                    <surname>Ferret</surname>
                  </persName>
                  <email type="md5">383cec00a00425ccdb255ad20191a98e</email>
                  <email type="domain">cea.fr</email>
                  <idno type="idhal" notation="string">olivier-ferret</idno>
                  <idno type="idhal" notation="numeric">14770</idno>
                  <idno type="halauthorid" notation="string">22591-14770</idno>
                  <idno type="IDREF">https://www.idref.fr/155894498</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0755-2361</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=-mCQhtIAAAAJ</idno>
                  <idno type="ARXIV">https://arxiv.org/a/ferret_o_1</idno>
                  <affiliation ref="#struct-241319"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hervé</forename>
                    <surname>Le Borgne</surname>
                  </persName>
                  <email type="md5">56ea649a249c59b0f72edac99322c287</email>
                  <email type="domain">cea.fr</email>
                  <idno type="idhal" notation="string">herve-le-borgne</idno>
                  <idno type="idhal" notation="numeric">181478</idno>
                  <idno type="halauthorid" notation="string">1029-181478</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0520-8436</idno>
                  <idno type="IDREF">https://www.idref.fr/079208452</idno>
                  <affiliation ref="#struct-241319"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Anne-Laure</forename>
                    <surname>Daquo</surname>
                  </persName>
                  <email type="md5">a8894d87c9a7f441330dab9bdcddf01c</email>
                  <email type="domain">cea.fr</email>
                  <idno type="idhal" notation="numeric">1035642</idno>
                  <idno type="halauthorid" notation="string">1411075-1035642</idno>
                  <affiliation ref="#struct-241319"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Youssef</forename>
                    <surname>Tamaazousti</surname>
                  </persName>
                  <idno type="halauthorid">1374829-0</idno>
                  <affiliation ref="#struct-241319"/>
                  <affiliation ref="#struct-435635"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>14ème COnférence en Recherche d'Information et Applications (CORIA 2017)</title>
                  <date type="start">2017</date>
                  <settlement>Marseille</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">185-200</biblScope>
                  <date type="datePub">2017</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Negative sample selection</term>
                <term xml:lang="en">Entity linking</term>
                <term xml:lang="en">Entity retrieval</term>
                <term xml:lang="en">Entity IR</term>
              </keywords>
              <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="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>The objective of Entity Linking is to connect an entity mention in a text to a knownentity in a knowledge base. The general approach for this task is to generate, for a givenmention, a set of candidate entities from the base and determine, in a second step, the bestone. This paper focuses on this last step and proposes a method based on learning a functionthat discriminates an entity from its most ambiguous ones. We adopt a model that is able todeal with large knowledge bases. Thus our contribution lies in the strategy to learn efficientlysuch a model. We propose three strategies with different efficiency/performance tradeoff. Theapproach is experimentally validated on six datasets of the TAC evaluation campaigns by usingFreebase and DBpedia as reference knowledge bases</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="department" xml:id="struct-241319" status="VALID">
          <idno type="RNSR">200822618E</idno>
          <orgName>Département Intelligence Ambiante et Systèmes Interactifs</orgName>
          <orgName type="acronym">DIASI (CEA, LIST)</orgName>
          <desc>
            <address>
              <addrLine>CEA Saclay - Nanoinnov 91191 Gif-Sur-Yvette Cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation name="DRT/LIST/DIASI" active="#struct-40217" type="direct"/>
            <relation name="DRT/LIST" active="#struct-440043" type="indirect"/>
            <relation name="DRT" active="#struct-300016" type="indirect"/>
            <relation active="#struct-419361" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-184143" status="OLD">
          <orgName>Laboratoire Vision et Ingénierie des Contenus</orgName>
          <orgName type="acronym">LVIC</orgName>
          <desc>
            <address>
              <addrLine>CEA Saclay Nano-INNOV Institut CEA LIST Point courrier n°173 91 191 Gif sur Yvette CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.kalisteo.fr</ref>
          </desc>
          <listRelation>
            <relation name="DRT/LIST/DIASI" active="#struct-241319" type="direct"/>
            <relation name="DRT/LIST/DIASI" active="#struct-40217" type="indirect"/>
            <relation name="DRT/LIST" active="#struct-440043" type="indirect"/>
            <relation name="DRT" active="#struct-300016" type="indirect"/>
            <relation active="#struct-419361" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-435635" status="OLD">
          <idno type="IdRef">14797299X</idno>
          <idno type="RNSR">200615286U</idno>
          <orgName>Mathématiques et Informatique pour la Complexité et les Systèmes</orgName>
          <orgName type="acronym">MICS</orgName>
          <date type="start">2015-09-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://mics.centralesupelec.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-411575" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-40217" status="VALID">
          <idno type="IdRef">156836882</idno>
          <idno type="ISNI">0000 0004 0405 1788</idno>
          <idno type="RNSR">200118591H</idno>
          <idno type="ROR">https://ror.org/000dbcc61</idno>
          <idno type="Wikidata">Q30299467</idno>
          <orgName>Laboratoire d'Intégration des Systèmes et des Technologies</orgName>
          <orgName type="acronym">LIST (CEA)</orgName>
          <desc>
            <address>
              <addrLine>DRT/LISTNano-INNOVAvenue de la Vauve91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www-list.cea.fr/</ref>
          </desc>
          <listRelation>
            <relation name="DRT/LIST" active="#struct-440043" type="direct"/>
            <relation name="DRT" active="#struct-300016" type="indirect"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-440043" status="VALID">
          <idno type="IdRef">067087930</idno>
          <idno type="ISNI">0000000121157881</idno>
          <idno type="RNSR">199018589D</idno>
          <idno type="ROR">https://ror.org/02ggzyd20</idno>
          <idno type="Wikidata">Q30299418</idno>
          <orgName>Direction de Recherche Technologique (CEA)</orgName>
          <orgName type="acronym">DRT (CEA)</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.drt-cea.com/</ref>
          </desc>
          <listRelation>
            <relation name="DRT" active="#struct-300016" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300016" status="VALID">
          <idno type="IdRef">026372061</idno>
          <idno type="ISNI">0000000122998025</idno>
          <idno type="ROR">https://ror.org/00jjx8s55</idno>
          <idno type="Wikidata">Q868550</idno>
          <orgName>Commissariat à l'énergie atomique et aux énergies alternatives</orgName>
          <orgName type="acronym">CEA</orgName>
          <desc>
            <address>
              <addrLine>Centre de SaclayCentre de GrenobleCentre de Cadaracheetc</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cea.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-419361" status="VALID">
          <idno type="IdRef">241345251</idno>
          <idno type="ROR">https://ror.org/03xjwb503</idno>
          <orgName>Université Paris-Saclay</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Bréguet, 3 Rue Joliot Curie 2e ét, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/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>
      </listOrg>
    </back>
  </text>
</TEI>