<?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-03991363</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="2026-05-21T04:59:29+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="fr">Extraction d'informations sur les workflows scientifiques à partir de la littérature</title>
            <author role="aut">
              <persName>
                <forename type="first">Clémence</forename>
                <surname>Sebe</surname>
              </persName>
              <email type="md5">5db55cea836318f78a3d8a1e1aba7e2b</email>
              <email type="domain">universite-paris-saclay.fr</email>
              <idno type="idhal" notation="string">clemence-sebe</idno>
              <idno type="idhal" notation="numeric">1227579</idno>
              <idno type="halauthorid" notation="string">2727915-1227579</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1988-1875</idno>
              <affiliation ref="#struct-1065372"/>
              <affiliation ref="#struct-1061259"/>
            </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-1062142"/>
              <affiliation ref="#struct-1065372"/>
              <affiliation ref="#struct-1061259"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sarah</forename>
                <surname>Cohen-Boulakia</surname>
              </persName>
              <email type="md5">37273ace89e7ffec8b1e6b59fab2d88a</email>
              <email type="domain">lri.fr</email>
              <idno type="idhal" notation="string">sarah-cohen-boulakia</idno>
              <idno type="idhal" notation="numeric">15627</idno>
              <idno type="halauthorid" notation="string">11783-15627</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=8QeCBlwAAAAJ&amp;hl=en</idno>
              <idno type="IDREF">https://www.idref.fr/09578960X</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7439-1441</idno>
              <idno type="VIAF">https://viaf.org/viaf/35641263</idno>
              <idno type="ISNI">http://isni.org/isni/0000000038166146</idno>
              <affiliation ref="#struct-1062146"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Alban</forename>
                <surname>Gaignard</surname>
              </persName>
              <email type="md5">77089e5bbd5467d5dfab160a4eb15c2a</email>
              <email type="domain">univ-nantes.fr</email>
              <idno type="idhal" notation="string">alban-gaignard</idno>
              <idno type="idhal" notation="numeric">1448</idno>
              <idno type="halauthorid" notation="string">39877-1448</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/D-1333-2018</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3597-8557</idno>
              <idno type="IDREF">https://www.idref.fr/170047830</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/D-1333-2018</idno>
              <idno type="VIAF">https://viaf.org/viaf/304847402</idno>
              <affiliation ref="#struct-1083366"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Aurélie</forename>
                <surname>Névéol</surname>
              </persName>
              <email type="md5">e940b30e4efdd83272c0245ca6255b44</email>
              <email type="domain">limsi.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-03-08 14:46:32</date>
              <date type="whenModified">2026-05-05 16:38:03</date>
              <date type="whenReleased">2023-03-09 11:26:12</date>
              <date type="whenProduced">2023-01-16</date>
              <date type="whenEndEmbargoed">2023-02-15</date>
              <ref type="file" target="https://hal.science/hal-03991363v1/document">
                <date notBefore="2023-02-15"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03991363v1/file/Sebe_EGC2023_revised.pdf" id="file-3991363-3500938">
                <date notBefore="2023-02-15"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="332014">
                <persName>
                  <forename>Aurélie</forename>
                  <surname>Névéol</surname>
                </persName>
                <email type="md5">e940b30e4efdd83272c0245ca6255b44</email>
                <email type="domain">limsi.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03991363</idno>
            <idno type="halUri">https://hal.science/hal-03991363</idno>
            <idno type="halBibtex">sebe:hal-03991363</idno>
            <idno type="halRefHtml">&lt;i&gt;23ème conférence francophone sur l'Extraction et la Gestion des Connaissances (EGC)&lt;/i&gt;, Jan 2023, Lyon, France. pp.313-320</idno>
            <idno type="halRef">23ème conférence francophone sur l'Extraction et la Gestion des Connaissances (EGC), Jan 2023, Lyon, France. pp.313-320</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3991363-3500938"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</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="LISN-BIOINFO" corresp="LISN">BioInformatique </idno>
            <idno type="stamp" n="LISN-ILES" corresp="LISN">Information, Langue Ecrite et Signée </idno>
            <idno type="stamp" n="NANTES-UNIVERSITE">Nantes Université</idno>
            <idno type="stamp" n="NANTES-UNIV">Nantes Université</idno>
            <idno type="stamp" n="LISN-STL">Sciences et Technologies des Langues</idno>
            <idno type="stamp" n="LINKED_RESEARCH_OUTPUTS">Publications linked to dataset and software</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="fr">Extraction d'informations sur les workflows scientifiques à partir de la littérature</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Clémence</forename>
                    <surname>Sebe</surname>
                  </persName>
                  <email type="md5">5db55cea836318f78a3d8a1e1aba7e2b</email>
                  <email type="domain">universite-paris-saclay.fr</email>
                  <idno type="idhal" notation="string">clemence-sebe</idno>
                  <idno type="idhal" notation="numeric">1227579</idno>
                  <idno type="halauthorid" notation="string">2727915-1227579</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1988-1875</idno>
                  <affiliation ref="#struct-1065372"/>
                  <affiliation ref="#struct-1061259"/>
                </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-1062142"/>
                  <affiliation ref="#struct-1065372"/>
                  <affiliation ref="#struct-1061259"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sarah</forename>
                    <surname>Cohen-Boulakia</surname>
                  </persName>
                  <email type="md5">37273ace89e7ffec8b1e6b59fab2d88a</email>
                  <email type="domain">lri.fr</email>
                  <idno type="idhal" notation="string">sarah-cohen-boulakia</idno>
                  <idno type="idhal" notation="numeric">15627</idno>
                  <idno type="halauthorid" notation="string">11783-15627</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=8QeCBlwAAAAJ&amp;hl=en</idno>
                  <idno type="IDREF">https://www.idref.fr/09578960X</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7439-1441</idno>
                  <idno type="VIAF">https://viaf.org/viaf/35641263</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000038166146</idno>
                  <affiliation ref="#struct-1062146"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Alban</forename>
                    <surname>Gaignard</surname>
                  </persName>
                  <email type="md5">77089e5bbd5467d5dfab160a4eb15c2a</email>
                  <email type="domain">univ-nantes.fr</email>
                  <idno type="idhal" notation="string">alban-gaignard</idno>
                  <idno type="idhal" notation="numeric">1448</idno>
                  <idno type="halauthorid" notation="string">39877-1448</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/D-1333-2018</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3597-8557</idno>
                  <idno type="IDREF">https://www.idref.fr/170047830</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/D-1333-2018</idno>
                  <idno type="VIAF">https://viaf.org/viaf/304847402</idno>
                  <affiliation ref="#struct-1083366"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>23ème conférence francophone sur l'Extraction et la Gestion des Connaissances (EGC)</title>
                  <date type="start">2023-01-16</date>
                  <date type="end">2023-01-20</date>
                  <settlement>Lyon</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <biblScope unit="volume">Extraction et Gestion des Connaissances, RNTI-E-39</biblScope>
                  <biblScope unit="pp">313-320</biblScope>
                  <date type="datePub">2023-01</date>
                </imprint>
              </monogr>
              <relatedItem target="https://doi.org/10.5281/zenodo.10650467" type="Cites" subtype="http://purl.org/coar/resource_type/c_ddb1"/>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</classCode>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</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>Scientific workflows provide bioinformaticians a mean to represent, exchange and ensure the reproducibility of their analysis pipelines. Workflows are described in literature (text) and/or stored in workflow repositories (code). A major challenge to ensure better workflow reuse is to rebuild the link between the documentation (text) and the workflow code. Based on workflow descriptions found in the full text of articles in English, we propose a method for representing and extracting information about the components of workflows. We present a corpus of 24 articles annotated with a schema made of 16 entities and 10 relations. We use this corpus to train and evaluate statistical models for extracting information about workflows. The results obtained show the feasibility of the task and are a first step towards the integration of workflow information from the literature and workflow repositories.</p>
            </abstract>
            <abstract xml:lang="fr">
              <p>Les workflows scientifiques offrent aux bioinformaticiens un cadre pour représenter, échanger et assurer la reproductibilité de leurs pipelines d'analyses. Ils sont décrits dans la littérature (texte) et/ou stockés dans des dépôts de workflows (code). Un enjeu majeur pour tendre vers une meilleure réutilisation des workflows par des tiers est de reconstruire le lien entre la documentation (texte) et l'implémentation (code) du workflow. A partir du texte intégral d'articles décrivant des workflows en anglais, nous proposons une méthode de modélisation et d'extraction d'informations des composants des workflows. Nous présentons un corpus de 24 articles annotés à l'aide d'un schéma comportant 16 entités et 10 relations. Nous utilisons ce corpus pour entraîner et évaluer des modèles statistiques d'extraction d'information sur les workflows. Nous montrons la faisabilité de la tâche comme première étape vers l'intégration d'information concernant les workflows issus de la littérature et des dépôts de workflows.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <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-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="researchteam" xml:id="struct-1062142" status="OLD">
          <orgName>Information, Langue Ecrite et Signée</orgName>
          <orgName type="acronym">ILES</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Université Paris-Saclay, Bâtiment 507, 91405 Orsay Cedex</addrLine>
              <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"/>
            <relation active="#struct-1065372" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1062146" status="VALID">
          <orgName>BioInformatique - LISN</orgName>
          <orgName type="acronym">BioInfo</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Université Paris-Saclay, Bâtiment 650, 91190 Gif-sur-Yvette</addrLine>
              <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"/>
            <relation active="#struct-1065371" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-1083366" status="VALID">
          <idno type="IdRef">258086599</idno>
          <idno type="ROR">https://ror.org/03gnr7b55</idno>
          <orgName>Nantes Université</orgName>
          <orgName type="acronym">Nantes Univ</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </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-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="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-1065371" status="VALID">
          <orgName>Science des Données</orgName>
          <orgName type="acronym">SDD</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>
      </listOrg>
    </back>
  </text>
</TEI>