<?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-04357157</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="2026-05-14T02:35:34+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Towards Multilingual Interlinear Morphological 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-1085231"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Shu</forename>
                <surname>OKABE</surname>
              </persName>
              <email type="md5">612d8917f2d8f0de8b1b3491808d0a7e</email>
              <email type="domain">tum.de</email>
            </editor>
            <funder ref="#projanr-50418"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-12-21 00:53:12</date>
              <date type="whenModified">2025-03-21 03:15:26</date>
              <date type="whenReleased">2023-12-26 16:02:48</date>
              <date type="whenProduced">2023-12-06</date>
              <date type="whenEndEmbargoed">2023-12-21</date>
              <ref type="file" target="https://hal.science/hal-04357157v1/document">
                <date notBefore="2023-12-21"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-04357157v1/file/2023.findings-emnlp.396.pdf" id="file-4357157-3792119">
                <date notBefore="2023-12-21"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1080814">
                <persName>
                  <forename>Shu</forename>
                  <surname>OKABE</surname>
                </persName>
                <email type="md5">612d8917f2d8f0de8b1b3491808d0a7e</email>
                <email type="domain">tum.de</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04357157</idno>
            <idno type="halUri">https://hal.science/hal-04357157</idno>
            <idno type="halBibtex">okabe:hal-04357157</idno>
            <idno type="halRefHtml">&lt;i&gt;2023 Conference on Empirical Methods in Natural Language Processing&lt;/i&gt;, Association for Computational Linguistics, Dec 2023, Singapore, Singapore. pp.5958-5971, &lt;a target="_blank" href="https://dx.doi.org/10.18653/v1/2023.findings-emnlp.396"&gt;&amp;#x27E8;10.18653/v1/2023.findings-emnlp.396&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">2023 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Dec 2023, Singapore, Singapore. pp.5958-5971, &amp;#x27E8;10.18653/v1/2023.findings-emnlp.396&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-sa/4.0/">CC BY-SA 4.0 - Attribution - ShareAlike<ref corresp="#file-4357157-3792119"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="ISIR" corresp="SORBONNE-UNIVERSITE">Institut des Systèmes Intelligents et de Robotique</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="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="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="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="ISIR_MLIA" corresp="ISIR">Machine Learning and Information Access</idno>
            <idno type="stamp" n="LISN-STL">Sciences et Technologies des Langues</idno>
            <idno type="stamp" n="SUPRA_INGENIERIE">Ingénierie</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">Towards Multilingual Interlinear Morphological 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-1085231"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Findings of the Association for Computational Linguistics: EMNLP 2023</title>
                <meeting>
                  <title>2023 Conference on Empirical Methods in Natural Language Processing</title>
                  <date type="start">2023-12-06</date>
                  <date type="end">2023-12-10</date>
                  <settlement>Singapore</settlement>
                  <country key="SG">Singapore</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>Association for Computational Linguistics</name>
                </respStmt>
                <imprint>
                  <publisher>Association for Computational Linguistics</publisher>
                  <biblScope unit="pp">5958-5971</biblScope>
                  <date type="datePub">2023-12-10</date>
                </imprint>
              </monogr>
              <idno type="doi">10.18653/v1/2023.findings-emnlp.396</idno>
              <ref type="publisher">https://aclanthology.org/2023.findings-emnlp.396/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Computational language documentation</term>
                <term xml:lang="en">Automatic glossing</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>Interlinear Morphological Glosses are annotations produced in the context of language documentation. Their goal is to identify morphs occurring in an L1 sentence and to explicit their function and meaning, with the further support of an associated translation in L2. We study here the task of automatic glossing, aiming to provide linguists with adequate tools to facilitate this process. Our formalisation of glossing uses a latent variable Conditional Random Field (CRF), which labels the L1 morphs while simultaneously aligning them to L2 words. In experiments with several under-resourced languages, we show that this approach is both effective and data-efficient and mitigates the problem of annotating unknown morphs. We also discuss various design choices regarding the alignment process and the selection of features. We finally demonstrate that it can benefit from multilingual (pre-)training, achieving results which outperform very strong baselines.</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="researchteam" xml:id="struct-1085231" status="VALID">
          <orgName>Machine Learning and Information Access</orgName>
          <orgName type="acronym">MLIA</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>Tour 65-66 3ème étage4, place Jussieu75005 Paris – France</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-541937" type="direct"/>
            <relation active="#struct-413221" type="indirect"/>
            <relation name="UMR7222" 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="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>
        <org type="laboratory" xml:id="struct-541937" status="VALID">
          <idno type="IdRef">241179122</idno>
          <idno type="RNSR">200918463J</idno>
          <idno type="ROR">05neq8668</idno>
          <orgName>Institut des Systèmes Intelligents et de Robotique</orgName>
          <orgName type="acronym">ISIR</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>Sorbonne-Université, Boite courrier 173 4 Place JUSSIEU 75252 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.isir.upmc.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-413221" type="direct"/>
            <relation name="UMR7222" active="#struct-441569" type="direct"/>
          </listRelation>
        </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>
      </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>