<?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-04623016v2</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="2026-04-28T19:30:47+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="fr">Reconnaissance d’entités cliniques en few-shot en trois langues</title>
            <author role="aut">
              <persName>
                <forename type="first">Marco</forename>
                <surname>Naguib</surname>
              </persName>
              <email type="md5">2199b9acbe4b12b1f098ad7634779e03</email>
              <email type="domain">hotmail.com</email>
              <idno type="idhal" notation="string">marconaguib</idno>
              <idno type="idhal" notation="numeric">1262326</idno>
              <idno type="halauthorid" notation="string">2504600-1262326</idno>
              <idno type="ORCID">https://orcid.org/0009-0008-2411-7031</idno>
              <idno type="ORCID">https://orcid.org/0009-0003-2950-8852</idno>
              <idno type="IDREF">https://www.idref.fr/290492718</idno>
              <affiliation ref="#struct-419361"/>
              <affiliation ref="#struct-1065372"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Aurélie</forename>
                <surname>Névéol</surname>
              </persName>
              <email type="md5">e940b30e4efdd83272c0245ca6255b44</email>
              <email type="domain">limsi.fr</email>
              <idno type="idhal" notation="string">aurelie-neveol</idno>
              <idno type="idhal" notation="numeric">20620</idno>
              <idno type="halauthorid" notation="string">6298-20620</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1846-9144</idno>
              <idno type="IDREF">https://www.idref.fr/094239428</idno>
              <affiliation ref="#struct-1065372"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Xavier</forename>
                <surname>Tannier</surname>
              </persName>
              <email type="md5">2bb58c32aed6ba0e82f442d1853eb8f9</email>
              <email type="domain">sorbonne-universite.fr</email>
              <idno type="idhal" notation="string">xtannier</idno>
              <idno type="idhal" notation="numeric">18076</idno>
              <idno type="halauthorid" notation="string">3654-18076</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2452-8868</idno>
              <idno type="IDREF">https://www.idref.fr/113391722</idno>
              <idno type="VIAF">https://viaf.org/viaf/159966816</idno>
              <idno type="ISNI">http://isni.org/isni/0000000356945129</idno>
              <affiliation ref="#struct-1001042"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Marco</forename>
                <surname>Naguib</surname>
              </persName>
              <email type="md5">9d5e9d9f723dfdd60301c24f612531d9</email>
              <email type="domain">universite-paris-saclay.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2024-07-01 09:13:44</date>
            </edition>
            <edition n="v2" type="current">
              <date type="whenSubmitted">2024-07-31 14:10:15</date>
              <date type="whenModified">2026-02-23 18:07:54</date>
              <date type="whenReleased">2024-07-31 14:38:00</date>
              <date type="whenProduced">2024-07-08</date>
              <date type="whenEndEmbargoed">2024-07-31</date>
              <ref type="file" target="https://inria.hal.science/hal-04623016v2/document">
                <date notBefore="2024-07-31"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-04623016v2/file/TALN2024_NAGUIB-1.pdf" id="file-4665584-4051712">
                <date notBefore="2024-07-31"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1395538">
                <persName>
                  <forename>Marco</forename>
                  <surname>Naguib</surname>
                </persName>
                <email type="md5">9d5e9d9f723dfdd60301c24f612531d9</email>
                <email type="domain">universite-paris-saclay.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04623016</idno>
            <idno type="halUri">https://inria.hal.science/hal-04623016</idno>
            <idno type="halBibtex">naguib:hal-04623016</idno>
            <idno type="halRefHtml">&lt;i&gt;31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024)&lt;/i&gt;, Jul 2024, Toulouse, France. pp.169-197</idno>
            <idno type="halRef">31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024), Jul 2024, Toulouse, France. pp.169-197</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4665584-4051712"/></licence>
            </availability>
          </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="LIMICS" corresp="SORBONNE-UNIVERSITE">Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SORBONNE-UNIV" corresp="SORBONNE-UNIVERSITE">Sorbonne Université 01/01/2018</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="SORBONNE-PARIS-NORD">Université Sorbonne Paris Nord</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="LISN">Laboratoire Interdisciplinaire des Sciences du Numérique</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="ACT-R" corresp="UNIV-PARIS13">Act'R </idno>
            <idno type="stamp" n="LISN-STL">Sciences et Technologies des Langues</idno>
            <idno type="stamp" n="PSACLAY-TEST">Université Paris-Saclay - Collection pour tests</idno>
            <idno type="stamp" n="SUPRA_INGENIERIE">Ingénierie</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">Reconnaissance d’entités cliniques en few-shot en trois langues</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Marco</forename>
                    <surname>Naguib</surname>
                  </persName>
                  <email type="md5">2199b9acbe4b12b1f098ad7634779e03</email>
                  <email type="domain">hotmail.com</email>
                  <idno type="idhal" notation="string">marconaguib</idno>
                  <idno type="idhal" notation="numeric">1262326</idno>
                  <idno type="halauthorid" notation="string">2504600-1262326</idno>
                  <idno type="ORCID">https://orcid.org/0009-0008-2411-7031</idno>
                  <idno type="ORCID">https://orcid.org/0009-0003-2950-8852</idno>
                  <idno type="IDREF">https://www.idref.fr/290492718</idno>
                  <affiliation ref="#struct-419361"/>
                  <affiliation ref="#struct-1065372"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Aurélie</forename>
                    <surname>Névéol</surname>
                  </persName>
                  <email type="md5">e940b30e4efdd83272c0245ca6255b44</email>
                  <email type="domain">limsi.fr</email>
                  <idno type="idhal" notation="string">aurelie-neveol</idno>
                  <idno type="idhal" notation="numeric">20620</idno>
                  <idno type="halauthorid" notation="string">6298-20620</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1846-9144</idno>
                  <idno type="IDREF">https://www.idref.fr/094239428</idno>
                  <affiliation ref="#struct-1065372"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Xavier</forename>
                    <surname>Tannier</surname>
                  </persName>
                  <email type="md5">2bb58c32aed6ba0e82f442d1853eb8f9</email>
                  <email type="domain">sorbonne-universite.fr</email>
                  <idno type="idhal" notation="string">xtannier</idno>
                  <idno type="idhal" notation="numeric">18076</idno>
                  <idno type="halauthorid" notation="string">3654-18076</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2452-8868</idno>
                  <idno type="IDREF">https://www.idref.fr/113391722</idno>
                  <idno type="VIAF">https://viaf.org/viaf/159966816</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000356945129</idno>
                  <affiliation ref="#struct-1001042"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">35èmes Journées d'Études sur la Parole (JEP 2024)</title>
                <meeting>
                  <title>31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024)</title>
                  <date type="start">2024-07-08</date>
                  <date type="end">2024-07-12</date>
                  <settlement>Toulouse</settlement>
                  <country key="FR">France</country>
                </meeting>
                <editor>BALAGUER</editor>
                <editor>Mathieu and BENDAHMAN</editor>
                <editor>Nihed and HO-DAC</editor>
                <editor>Lydia-Mai and MAUCLAIR</editor>
                <editor>Julie and MORENO</editor>
                <editor>Jose G and PINQUIER</editor>
                <editor>Julien</editor>
                <imprint>
                  <publisher>ATALA &amp; AFPC</publisher>
                  <biblScope unit="volume">1 : articles longs et prises de position</biblScope>
                  <biblScope unit="pp">169-197</biblScope>
                  <date type="datePub">2024</date>
                </imprint>
              </monogr>
              <relatedItem target="https://inria.hal.science/hal-04623005v1" type="IsPartOf" subtype="http://purl.org/coar/resource_type/c_18cf"/>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">few-shot learning</term>
                <term xml:lang="en">large language models</term>
                <term xml:lang="en">named entity recognition</term>
                <term xml:lang="fr">Apprentissage en few-shot</term>
                <term xml:lang="fr">modèles de langues</term>
                <term xml:lang="fr">reconnaissance d’entités nommées</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</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>Large language models have become the preferred solution for many natural language processing tasks, including specialized domains where their few-shot capabilities should deliver high performance in low-resource environments. However, our evaluation of 10 auto-regressive models and 16 masked models shows that while prompt-based auto-regressive models can compete in named entity recognition (NER) outside the clinical domain, they are outperformed within the clinical domain by lighter biLSTM-CRF taggers based on masked models. Additionally, masked models have a much lower environmental impact than auto-regressive models. These consistent results across the three languages studied suggest that few-shot learning models are not yet suited for NER production in the clinical domain but could be used to expedite the creation of quality annotated data</p>
            </abstract>
            <abstract xml:lang="fr">
              <p>Les grands modèles de langage deviennent la solution de choix pour de nombreuses tâches de traitement du langage naturel, y compris dans des domaines spécialisés où leurs capacités few-shot devraient permettre d’obtenir des performances élevées dans des environnements à faibles ressources. Cependant, notre évaluation de 10 modèles auto-régressifs et 16 modèles masqués montre que, bien que les modèles auto-régressifs utilisant des prompts puissent rivaliser en termes de reconnaissance d’entités nommées (REN) en dehors du domaine clinique, ils sont dépassés dans le domaine clinique par des taggers biLSTM-CRF plus légers reposant sur des modèles masqués. De plus, les modèles masqués ont un bien moindre impact environnemental que les modèles auto-régressifs. Ces résultats, cohérents dans les trois langues étudiées, suggèrent que les modèles à apprentissage few-shot ne sont pas encore adaptés à la production de REN dans le domaine clinique, mais pourraient être utilisés pour accélérer la création de données annotées de qualité.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <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="department" xml:id="struct-1065372" status="VALID">
          <orgName>Sciences et Technologies des Langues - LISN</orgName>
          <orgName type="acronym">STL</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1061259" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-419361" type="indirect"/>
            <relation name="UMR9015" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1001042" status="VALID">
          <idno type="IdRef">190100990</idno>
          <idno type="RNSR">201420870D</idno>
          <idno type="ROR">https://ror.org/01jr1v359</idno>
          <orgName>Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé</orgName>
          <orgName type="acronym">LIMICS</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Campus des Cordeliers/Escalier D - 15 rue de l'Ecole de Médecine 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ics.upmc.fr/</ref>
          </desc>
          <listRelation>
            <relation name="U1142" active="#struct-303623" type="direct"/>
            <relation name="UMRS_1142" active="#struct-413221" type="direct"/>
            <relation active="#struct-581146" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1061259" status="VALID">
          <idno type="IdRef">253160316</idno>
          <idno type="RNSR">202123711L</idno>
          <idno type="ROR">https://ror.org/00rd81916</idno>
          <idno type="Wikidata">Q109620676</idno>
          <orgName>Laboratoire Interdisciplinaire des Sciences du Numérique</orgName>
          <orgName type="acronym">LISN</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Universitaire bât 507Rue du Belvédère91405 Orsay cedexet Campus Universitaire bât 6401 rue Raimond Castaing91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lisn.upsaclay.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UMR9015" 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="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="institution" xml:id="struct-303623" status="VALID">
          <idno type="IdRef">026388278</idno>
          <idno type="ROR">https://ror.org/02vjkv261</idno>
          <orgName>Institut National de la Santé et de la Recherche Médicale</orgName>
          <orgName type="acronym">INSERM</orgName>
          <desc>
            <address>
              <addrLine>101, rue de Tolbiac, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inserm.fr</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-413221" status="VALID">
          <idno type="IdRef">221333754</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Sorbonne Université</orgName>
          <orgName type="acronym">SU</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>21 rue de l’École de médecine - 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-universite.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-581146" status="VALID">
          <idno type="IdRef">02640463X</idno>
          <idno type="ISNI">0000000121496883</idno>
          <idno type="ROR">https://ror.org/0199hds37</idno>
          <orgName>Université Sorbonne Paris Nord</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>99, avenue Jean-Baptiste Clément, 93430 Villetaneuse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-paris13.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>