<?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-03832874</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="2026-05-17T05:59:37+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging</title>
            <author role="aut">
              <persName>
                <forename type="first">Ayyoob</forename>
                <surname>Imani</surname>
              </persName>
              <email type="md5">d1d64094d670dc88dc590c858b0fb27b</email>
              <email type="domain">cis.lmu.de</email>
              <idno type="idhal" notation="numeric">1116382</idno>
              <idno type="halauthorid" notation="string">2334485-1116382</idno>
              <affiliation ref="#struct-460393"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Silvia</forename>
                <surname>Severini</surname>
              </persName>
              <email type="md5">58a88e5d71506b28db97ee370d17227d</email>
              <email type="domain">cis.lmu.de</email>
              <idno type="idhal" notation="numeric">1179901</idno>
              <idno type="halauthorid" notation="string">2625379-1179901</idno>
              <affiliation ref="#struct-460393"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Masoud</forename>
                <forename type="middle">Jalili</forename>
                <surname>Sabet</surname>
              </persName>
              <email type="md5">4ec7babb2f85058567d0268dc000583c</email>
              <email type="domain">cis.lmu.de</email>
              <idno type="idhal" notation="numeric">1116383</idno>
              <idno type="halauthorid" notation="string">2334486-1116383</idno>
              <affiliation ref="#struct-460393"/>
            </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>
            <author role="aut">
              <persName>
                <forename type="first">Hinrich</forename>
                <surname>Schütze</surname>
              </persName>
              <idno type="halauthorid">2076347-0</idno>
              <affiliation ref="#struct-460393"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>François</forename>
                <surname>Yvon</surname>
              </persName>
              <email type="md5">c62025aca0c6cf8d65b4fe9600c991af</email>
              <email type="domain">cnrs.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-10-28 09:00:31</date>
              <date type="whenModified">2026-01-27 14:46:04</date>
              <date type="whenReleased">2022-11-02 08:57:09</date>
              <date type="whenProduced">2022-12-07</date>
              <date type="whenEndEmbargoed">2022-10-28</date>
              <ref type="file" target="https://hal.science/hal-03832874v1/document">
                <date notBefore="2022-10-28"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03832874v1/file/2210.09840.pdf" id="file-3832874-3352509">
                <date notBefore="2022-10-28"/>
              </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-03832874</idno>
            <idno type="halUri">https://hal.science/hal-03832874</idno>
            <idno type="halBibtex">imani:hal-03832874</idno>
            <idno type="halRefHtml">&lt;i&gt;Empirical Methods in Natural Language Processing&lt;/i&gt;, Association for Computational Linguistics, Dec 2022, Abu Dhabi, United Arab Emirates</idno>
            <idno type="halRef">Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Dec 2022, Abu Dhabi, United Arab Emirates</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3832874-3352509"/></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-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">Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Ayyoob</forename>
                    <surname>Imani</surname>
                  </persName>
                  <email type="md5">d1d64094d670dc88dc590c858b0fb27b</email>
                  <email type="domain">cis.lmu.de</email>
                  <idno type="idhal" notation="numeric">1116382</idno>
                  <idno type="halauthorid" notation="string">2334485-1116382</idno>
                  <affiliation ref="#struct-460393"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Silvia</forename>
                    <surname>Severini</surname>
                  </persName>
                  <email type="md5">58a88e5d71506b28db97ee370d17227d</email>
                  <email type="domain">cis.lmu.de</email>
                  <idno type="idhal" notation="numeric">1179901</idno>
                  <idno type="halauthorid" notation="string">2625379-1179901</idno>
                  <affiliation ref="#struct-460393"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Masoud</forename>
                    <forename type="middle">Jalili</forename>
                    <surname>Sabet</surname>
                  </persName>
                  <email type="md5">4ec7babb2f85058567d0268dc000583c</email>
                  <email type="domain">cis.lmu.de</email>
                  <idno type="idhal" notation="numeric">1116383</idno>
                  <idno type="halauthorid" notation="string">2334486-1116383</idno>
                  <affiliation ref="#struct-460393"/>
                </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>
                <author role="aut">
                  <persName>
                    <forename type="first">Hinrich</forename>
                    <surname>Schütze</surname>
                  </persName>
                  <idno type="halauthorid">2076347-0</idno>
                  <affiliation ref="#struct-460393"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Findings of the ACL: EMNLP 2022</title>
                <meeting>
                  <title>Empirical Methods in Natural Language Processing</title>
                  <date type="start">2022-12-07</date>
                  <date type="end">2022-12-09</date>
                  <settlement>Abu Dhabi</settlement>
                  <country key="AE">United Arab Emirates</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>Association for Computational Linguistics</name>
                </respStmt>
                <imprint/>
              </monogr>
              <ref type="publisher">https://2022.emnlp.org/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Natural Language Processing</term>
                <term xml:lang="en">Cross-lingual Transfer</term>
                <term xml:lang="en">PoS-tagging</term>
                <term xml:lang="fr">Traitement automatique des langues</term>
                <term xml:lang="fr">Etiquetage en parties du discours</term>
                <term xml:lang="fr">Transfert Cross-lingue</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</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>Part-of-Speech (POS) tagging is an important component of the NLP pipeline, but many lowresource languages lack labeled data for training. An established method for training a POS tagger in such a scenario is to create a labeled training set by transferring from high-resource languages. In this paper, we propose a novel method for transferring labels from multiple high-resource source to low-resource target languages. We formalize POS tag projection as graph-based label propagation. Given translations of a sentence in multiple languages, we create a graph with words as nodes and alignment links as edges by aligning words for all language pairs. We then propagate node labels from source to target using a Graph Neural Network augmented with transformer layers. We show that our propagation creates training sets that allow us to train POS taggers for a diverse set of languages. When combined with enhanced contextualized embeddings, our method achieves a new state-ofthe-art for unsupervised POS tagging of low resource languages.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-460393" status="VALID">
          <idno type="ROR">https://ror.org/05591te55</idno>
          <orgName>Ludwig Maximilian University [Munich] = Ludwig Maximilians Universität München</orgName>
          <orgName type="acronym">LMU</orgName>
          <date type="start">1472-01-01</date>
          <desc>
            <address>
              <addrLine>Professor-Huber-Platz 2, 80539 München, Allemagne</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.lmu.de/en/about-lmu/index.html</ref>
          </desc>
        </org>
        <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>
    </back>
  </text>
</TEI>