<?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-04623049</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="2026-04-28T19:32:15+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">astroECR : an Enriched Corpus for Astrophysical Entities, Coreferences, and Relations</title>
            <title xml:lang="fr">astroECR : enrichissement d'un corpus astrophysique en entités nommées, coréférences et relations sémantiques</title>
            <author role="aut">
              <persName>
                <forename type="first">Atilla Kaan</forename>
                <surname>Alkan</surname>
              </persName>
              <email type="md5">848ff209bbaee51769c9fbc2ccc4810b</email>
              <email type="domain">lisn.upsaclay.fr</email>
              <idno type="idhal" notation="string">atilla-alkan</idno>
              <idno type="idhal" notation="numeric">1262351</idno>
              <idno type="halauthorid" notation="string">2260829-1262351</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=_b6iBawAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/283001089</idno>
              <affiliation ref="#struct-1061259"/>
              <affiliation ref="#struct-53946"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Felix</forename>
                <surname>Grezes</surname>
              </persName>
              <idno type="halauthorid">3181201-0</idno>
              <affiliation ref="#struct-88749"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cyril</forename>
                <surname>Grouin</surname>
              </persName>
              <email type="md5">a7f1f504b2889f935ff469a8eb0f15d3</email>
              <email type="domain">limsi.fr</email>
              <idno type="idhal" notation="string">cyril-grouin</idno>
              <idno type="idhal" notation="numeric">177247</idno>
              <idno type="halauthorid" notation="string">12926-177247</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5809-188X</idno>
              <idno type="IDREF">https://www.idref.fr/163639132</idno>
              <idno type="VIAF">https://viaf.org/viaf/250874906</idno>
              <idno type="ISNI">http://isni.org/isni/0000000371327732</idno>
              <affiliation ref="#struct-1065372"/>
              <affiliation ref="#struct-1061259"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Fabian</forename>
                <surname>Schüssler</surname>
              </persName>
              <email type="md5">c2033b90ca5d44bb51d72c5c09c1e808</email>
              <email type="domain">cea.fr</email>
              <idno type="idhal" notation="string">fabian-schussler</idno>
              <idno type="idhal" notation="numeric">1344025</idno>
              <idno type="halauthorid" notation="string">1193519-1344025</idno>
              <idno type="ARXIV">https://arxiv.org/a/schussler_f_1</idno>
              <affiliation ref="#struct-53946"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Pierre</forename>
                <surname>Zweigenbaum</surname>
              </persName>
              <email type="md5">875a8768fc7f867a01a904fe839de31d</email>
              <email type="domain">limsi.fr</email>
              <idno type="idhal" notation="string">pierre-zweigenbaum</idno>
              <idno type="idhal" notation="numeric">14995</idno>
              <idno type="halauthorid" notation="string">1218-14995</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-8410-4808</idno>
              <idno type="IDREF">https://www.idref.fr/06664268X</idno>
              <affiliation ref="#struct-1065372"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Matthieu</forename>
                <surname>Labeau</surname>
              </persName>
              <email type="md5">3414152dcb8870e2d10b4ccfe4cdc5f2</email>
              <email type="domain">telecom-paris.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-07-01 09:13:50</date>
              <date type="whenModified">2025-03-21 03:15:35</date>
              <date type="whenReleased">2024-07-01 11:17:33</date>
              <date type="whenProduced">2024-07-08</date>
              <date type="whenEndEmbargoed">2024-07-01</date>
              <ref type="file" target="https://inria.hal.science/hal-04623049v1/document">
                <date notBefore="2024-07-01"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://inria.hal.science/hal-04623049v1/file/7664.pdf" id="file-4629977-4019256">
                <date notBefore="2024-07-01"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="850749">
                <persName>
                  <forename>Matthieu</forename>
                  <surname>Labeau</surname>
                </persName>
                <email type="md5">3414152dcb8870e2d10b4ccfe4cdc5f2</email>
                <email type="domain">telecom-paris.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04623049</idno>
            <idno type="halUri">https://inria.hal.science/hal-04623049</idno>
            <idno type="halBibtex">alkan:hal-04623049</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.720-733</idno>
            <idno type="halRef">31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024), Jul 2024, Toulouse, France. pp.720-733</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4629977-4019256"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CEA">CEA - Commissariat à l'énergie atomique</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="DSM-IRFU" corresp="CEA">IRFU</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</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-DRF" corresp="CEA">Direction de Recherche Fondamentale</idno>
            <idno type="stamp" n="TALN-RECITAL">Conférences TALN RECITAL</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-STL">Sciences et Technologies des Langues</idno>
            <idno type="stamp" n="JEP-TALN-RECITAL2024" corresp="TALN-RECITAL">CONFÉRENCE JEP TALN RECITAL 2024</idno>
            <idno type="stamp" n="PSACLAY-TEST">Université Paris-Saclay - Collection pour tests</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="en">astroECR : an Enriched Corpus for Astrophysical Entities, Coreferences, and Relations</title>
                <title xml:lang="fr">astroECR : enrichissement d'un corpus astrophysique en entités nommées, coréférences et relations sémantiques</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Atilla Kaan</forename>
                    <surname>Alkan</surname>
                  </persName>
                  <email type="md5">848ff209bbaee51769c9fbc2ccc4810b</email>
                  <email type="domain">lisn.upsaclay.fr</email>
                  <idno type="idhal" notation="string">atilla-alkan</idno>
                  <idno type="idhal" notation="numeric">1262351</idno>
                  <idno type="halauthorid" notation="string">2260829-1262351</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=_b6iBawAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/283001089</idno>
                  <affiliation ref="#struct-1061259"/>
                  <affiliation ref="#struct-53946"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Felix</forename>
                    <surname>Grezes</surname>
                  </persName>
                  <idno type="halauthorid">3181201-0</idno>
                  <affiliation ref="#struct-88749"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cyril</forename>
                    <surname>Grouin</surname>
                  </persName>
                  <email type="md5">a7f1f504b2889f935ff469a8eb0f15d3</email>
                  <email type="domain">limsi.fr</email>
                  <idno type="idhal" notation="string">cyril-grouin</idno>
                  <idno type="idhal" notation="numeric">177247</idno>
                  <idno type="halauthorid" notation="string">12926-177247</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5809-188X</idno>
                  <idno type="IDREF">https://www.idref.fr/163639132</idno>
                  <idno type="VIAF">https://viaf.org/viaf/250874906</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000371327732</idno>
                  <affiliation ref="#struct-1065372"/>
                  <affiliation ref="#struct-1061259"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Fabian</forename>
                    <surname>Schüssler</surname>
                  </persName>
                  <email type="md5">c2033b90ca5d44bb51d72c5c09c1e808</email>
                  <email type="domain">cea.fr</email>
                  <idno type="idhal" notation="string">fabian-schussler</idno>
                  <idno type="idhal" notation="numeric">1344025</idno>
                  <idno type="halauthorid" notation="string">1193519-1344025</idno>
                  <idno type="ARXIV">https://arxiv.org/a/schussler_f_1</idno>
                  <affiliation ref="#struct-53946"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Pierre</forename>
                    <surname>Zweigenbaum</surname>
                  </persName>
                  <email type="md5">875a8768fc7f867a01a904fe839de31d</email>
                  <email type="domain">limsi.fr</email>
                  <idno type="idhal" notation="string">pierre-zweigenbaum</idno>
                  <idno type="idhal" notation="numeric">14995</idno>
                  <idno type="halauthorid" notation="string">1218-14995</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-8410-4808</idno>
                  <idno type="IDREF">https://www.idref.fr/06664268X</idno>
                  <affiliation ref="#struct-1065372"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 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>
                <imprint>
                  <publisher>ATALA &amp; AFPC</publisher>
                  <biblScope unit="volume">1 : articles longs et prises de position</biblScope>
                  <biblScope unit="pp">720-733</biblScope>
                  <date type="datePub">2024</date>
                </imprint>
              </monogr>
              <ref type="publisher">https://jep-taln2024.sciencesconf.org/</ref>
              <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">Corpus Annotation</term>
                <term xml:lang="en">Information Extraction</term>
                <term xml:lang="en">Astrophysics</term>
                <term xml:lang="fr">Annotation de corpus</term>
                <term xml:lang="fr">Extraction d'information</term>
                <term xml:lang="fr">Astrophysique</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>The lack of annotated resources poses a significant challenge for natural language processing in astrophysics. To address this gap, we introduce astroECR, an extension of the TDAC (Time-Domain Astrophysics Corpus). This corpus, comprised of 300 observation reports in English, expands the initial annotation scheme of TDAC by introducing five additional named entity classes specific to astrophysics. We enhanced annotations to include coreferences, semantic relations between celestial objects and their physical properties, and normalization of celestial object names using astronomical databases. We demonstrate our corpus’s utility by providing baseline scores across four tasks : named entity recognition, coreference resolution, relation detection, and normalization of celestial object names. We provide the corpus, annotation guide, source code, and associated models to the community.</p>
            </abstract>
            <abstract xml:lang="fr">
              <p>Le manque de ressources annotées constitue un défi majeur pour le traitement automatique de la langue en astrophysique. Afin de combler cette lacune, nous présentons astroECR, une extension du corpus TDAC (Time-Domain Astrophysics Corpus). Notre corpus, constitué de 300 rapports d'observation en anglais, étend le schéma d'annotation initial de TDAC en introduisant cinq classes d'entités nommées supplémentaires spécifiques à l'astrophysique. Nous avons enrichi les annotations en incluant les coréférences, les relations sémantiques entre les objets célestes et leurs propriétés physiques, ainsi qu'en normalisant les noms d'objets célestes via des bases de données astronomiques. L'utilité de notre corpus est démontrée en fournissant des scores de référence à travers quatre tâches~ : la reconnaissance d'entités nommées, la résolution de coréférences, la détection de relations, et la normalisation des noms d'objets célestes. Nous mettons à disposition le corpus ainsi que son guide d'annotation, les codes sources, et les modèles associés.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <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="laboratory" xml:id="struct-53946" status="VALID">
          <idno type="IdRef">18202492X</idno>
          <idno type="ISNI">0000 0004 0619 0319</idno>
          <idno type="RNSR">199118599K</idno>
          <idno type="ROR">https://ror.org/05k705z76</idno>
          <orgName>Institut de Recherches sur les lois Fondamentales de l'Univers</orgName>
          <orgName type="acronym">IRFU</orgName>
          <desc>
            <address>
              <addrLine>CEA SaclayF-91191 Gif sur Yvette cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://irfu.cea.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-419361" type="direct"/>
            <relation active="#struct-465913" type="direct"/>
            <relation active="#struct-300016" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-88749" status="VALID">
          <idno type="ROR">https://ror.org/03c3r2d17</idno>
          <orgName>Harvard-Smithsonian Center for Astrophysics</orgName>
          <orgName type="acronym">CfA</orgName>
          <desc>
            <address>
              <addrLine>60 Garden Street, Cambridge, MA 02138, USA</addrLine>
              <country key="US"/>
            </address>
            <ref type="url">http://www.cfa.harvard.edu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-38302" type="direct"/>
            <relation active="#struct-300511" type="direct"/>
          </listRelation>
        </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="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="regrouplaboratory" xml:id="struct-465913" status="VALID">
          <idno type="IdRef">251118436</idno>
          <idno type="RNSR">201622496M</idno>
          <idno type="ROR">https://ror.org/01yvj5k91</idno>
          <idno type="Wikidata">Q52604525</idno>
          <orgName>Direction de Recherche Fondamentale (CEA)</orgName>
          <orgName type="acronym">DRF (CEA)</orgName>
          <date type="start">2016-01-01</date>
          <desc>
            <address>
              <addrLine>Direction de Recherche FondamentaleFundamental Research DivisionCEA Saclay91191 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ceasciences.fr/</ref>
          </desc>
          <listRelation>
            <relation 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-38302" status="VALID">
          <idno type="IdRef">026453169</idno>
          <idno type="ROR">https://ror.org/03vek6s52</idno>
          <orgName>Harvard University</orgName>
          <desc>
            <address>
              <addrLine>Massachusetts Hall, Cambridge, MA 02138</addrLine>
              <country key="US"/>
            </address>
            <ref type="url">http://www.harvard.edu/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-300511" status="VALID">
          <idno type="ROR">https://ror.org/01pp8nd67</idno>
          <orgName>Smithsonian Institution</orgName>
          <desc>
            <address>
              <addrLine>PO Box 37012, Washington, DC 20013-7012</addrLine>
              <country key="US"/>
            </address>
            <ref type="url">https://www.si.edu</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>