<?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-04186388</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="2026-05-22T15:03:19+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">LISN @ SIGMORPHON 2023 Shared Task on Interlinear Glossing</title>
            <author role="aut">
              <persName>
                <forename type="first">Shu</forename>
                <surname>Okabe</surname>
              </persName>
              <email type="md5">d9ab6f74b20269e72c964143c9c2f285</email>
              <email type="domain">limsi.fr</email>
              <idno type="idhal" notation="string">shu-okabe</idno>
              <idno type="idhal" notation="numeric">751379</idno>
              <idno type="halauthorid" notation="string">55347-751379</idno>
              <idno type="ORCID">https://orcid.org/0009-0003-0169-3689</idno>
              <idno type="IDREF">https://www.idref.fr/27562482X</idno>
              <affiliation ref="#struct-1062143"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">François</forename>
                <surname>Yvon</surname>
              </persName>
              <email type="md5">c62025aca0c6cf8d65b4fe9600c991af</email>
              <email type="domain">cnrs.fr</email>
              <idno type="idhal" notation="string">francois-yvon</idno>
              <idno type="idhal" notation="numeric">5347</idno>
              <idno type="halauthorid" notation="string">2529017-5347</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7972-7442</idno>
              <idno type="IDREF">https://www.idref.fr/057593531</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=JjfDvawAAAAJ</idno>
              <idno type="ARXIV">https://arxiv.org/a/yvon_f_1</idno>
              <affiliation ref="#struct-1062143"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>François</forename>
                <surname>Yvon</surname>
              </persName>
              <email type="md5">c62025aca0c6cf8d65b4fe9600c991af</email>
              <email type="domain">cnrs.fr</email>
            </editor>
            <funder ref="#projanr-50418"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-08-23 16:41:13</date>
              <date type="whenModified">2025-03-21 03:15:23</date>
              <date type="whenReleased">2023-08-24 16:53:30</date>
              <date type="whenProduced">2023-07-14</date>
              <date type="whenEndEmbargoed">2023-08-23</date>
              <ref type="file" target="https://hal.science/hal-04186388v1/document">
                <date notBefore="2023-08-23"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-04186388v1/file/2023.sigmorphon-1.21.pdf" id="file-4186388-3649861">
                <date notBefore="2023-08-23"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="164853">
                <persName>
                  <forename>François</forename>
                  <surname>Yvon</surname>
                </persName>
                <email type="md5">c62025aca0c6cf8d65b4fe9600c991af</email>
                <email type="domain">cnrs.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04186388</idno>
            <idno type="halUri">https://hal.science/hal-04186388</idno>
            <idno type="halBibtex">okabe:hal-04186388</idno>
            <idno type="halRefHtml">&lt;i&gt;The 20th SIGMORPHON workshop on Computational Morphology, Phonology, and Phonetics&lt;/i&gt;, Association for computational linguistics, Jul 2023, Toronto, Canada. &lt;a target="_blank" href="https://dx.doi.org/10.18653/v1/2023.sigmorphon-1.21"&gt;&amp;#x27E8;10.18653/v1/2023.sigmorphon-1.21&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">The 20th SIGMORPHON workshop on Computational Morphology, Phonology, and Phonetics, Association for computational linguistics, Jul 2023, Toronto, Canada. &amp;#x27E8;10.18653/v1/2023.sigmorphon-1.21&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4186388-3649861"/></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="ANR">ANR</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-TLP" corresp="LISN">Traitement du Langage Parlé </idno>
            <idno type="stamp" n="LISN-STL">Sciences et Technologies des Langues</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">LISN @ SIGMORPHON 2023 Shared Task on Interlinear Glossing</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Shu</forename>
                    <surname>Okabe</surname>
                  </persName>
                  <email type="md5">d9ab6f74b20269e72c964143c9c2f285</email>
                  <email type="domain">limsi.fr</email>
                  <idno type="idhal" notation="string">shu-okabe</idno>
                  <idno type="idhal" notation="numeric">751379</idno>
                  <idno type="halauthorid" notation="string">55347-751379</idno>
                  <idno type="ORCID">https://orcid.org/0009-0003-0169-3689</idno>
                  <idno type="IDREF">https://www.idref.fr/27562482X</idno>
                  <affiliation ref="#struct-1062143"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">François</forename>
                    <surname>Yvon</surname>
                  </persName>
                  <email type="md5">c62025aca0c6cf8d65b4fe9600c991af</email>
                  <email type="domain">cnrs.fr</email>
                  <idno type="idhal" notation="string">francois-yvon</idno>
                  <idno type="idhal" notation="numeric">5347</idno>
                  <idno type="halauthorid" notation="string">2529017-5347</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7972-7442</idno>
                  <idno type="IDREF">https://www.idref.fr/057593531</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=JjfDvawAAAAJ</idno>
                  <idno type="ARXIV">https://arxiv.org/a/yvon_f_1</idno>
                  <affiliation ref="#struct-1062143"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of the  20th SIGMORPHON workshop on Computational Morphology, Phonology, and Phonetics</title>
                <meeting>
                  <title>The 20th SIGMORPHON workshop on Computational Morphology, Phonology, and Phonetics</title>
                  <date type="start">2023-07-14</date>
                  <date type="end">2023-07-14</date>
                  <settlement>Toronto</settlement>
                  <country key="CA">Canada</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>Association for computational linguistics</name>
                </respStmt>
                <imprint/>
              </monogr>
              <idno type="doi">10.18653/v1/2023.sigmorphon-1.21</idno>
              <ref type="publisher">https://aclanthology.org/2023.sigmorphon-1.21</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Morphological segmentation</term>
                <term xml:lang="en">Automatic Glossing</term>
                <term xml:lang="en">Computational language documentation</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>This paper describes LISN's submission to the second track (open track) of the shared task on Interlinear Glossing for SIGMORPHON 2023. Our systems are based on Lost, a variation of linear Conditional Random Fields initially developed as a probabilistic translation model and then adapted to the glossing task. This model allows us to handle one of the main challenges posed by glossing, i.e. the fact that the list of potential labels for lexical morphemes is not fixed in advance and needs to be extended dynamically when labelling units are not seen in training. In such situations, we show how to make use of candidate lexical glosses found in the translation and discuss how such extension affects the training and inference procedures. The resulting automatic glossing systems prove to yield very competitive results, especially in low-resource settings.</p>
            </abstract>
            <abstract xml:lang="fr">
              <p>Cet article décrit la soumission du LISN à la deuxième piste (piste ouverte) de la tâche partagée sur la génération de gloses interlinéaires pour SIGMORPHON 2023. Nos systèmes sont basés sur Lost, qui met en oeuvre une variante des champs aléatoires conditionnels linéaires, initialement développée comme un modèle de traduction probabiliste et ensuite adaptée à la tâche de la génération de gloses. Ce modèle nous permet de gérer l'un des principaux défis posés par cette tâche, à savoir le fait que la liste des étiquettes potentielles pour les morphèmes lexicaux n'est pas fixée à l'avance et doit être étendue dynamiquement lorsque des étiquettes ne sont pas vues lors de l'entraînement. Dans de telles situations, nous montrons comment utiliser les gloses lexicales candidates trouvées dans la traduction et discutons de la manière dont cette extension affecte les procédures d'apprentissage et d'inférence. Les systèmes de génération automatique de gloses qui en résultent donnent des résultats très compétitifs, en particulier lorsque les ressources d'apprentissage sont limitées.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1062143" status="OLD">
          <orgName>Traitement du Langage Parlé - LISN</orgName>
          <orgName type="acronym">TLP</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="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="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-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>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-50418" status="VALID">
          <idno type="anr">ANR-19-CE38-0015</idno>
          <orgName>CLD2025</orgName>
          <desc>La documentation computationnelle des langues à l'horizon 2025</desc>
          <date type="start">2019</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>