<?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-04468022</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="2026-05-21T06:06:40+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Detecting Non-literal Translations by Fine-tuning Cross-lingual Pre-trained Language Models</title>
            <author role="aut">
              <persName>
                <forename type="first">Yuming</forename>
                <surname>Zhai</surname>
              </persName>
              <email type="md5">c24b9b87db9aeb09a9a5d6233f97f79c</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">yuming-zhai</idno>
              <idno type="idhal" notation="numeric">20611</idno>
              <idno type="halauthorid" notation="string">40422-20611</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3597-2833</idno>
              <idno type="IDREF">https://www.idref.fr/242113648</idno>
              <affiliation ref="#struct-1041998"/>
              <affiliation ref="#struct-1041968"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gabriel</forename>
                <surname>Illouz</surname>
              </persName>
              <email type="md5">e63c74600c9b1282a3609d48a655f6bd</email>
              <email type="domain">limsi.fr</email>
              <idno type="idhal" notation="numeric">1053645</idno>
              <idno type="halauthorid" notation="string">156920-1053645</idno>
              <idno type="IDREF">https://www.idref.fr/293677522</idno>
              <affiliation ref="#struct-1041998"/>
              <affiliation ref="#struct-1041968"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Anne</forename>
                <surname>Vilnat</surname>
              </persName>
              <email type="md5">9ce78ed5537add2d6066d4c3c6fd501e</email>
              <email type="domain">limsi.fr</email>
              <idno type="idhal" notation="string">anne-vilnat</idno>
              <idno type="idhal" notation="numeric">174170</idno>
              <idno type="halauthorid" notation="string">11967-174170</idno>
              <idno type="IDREF">https://www.idref.fr/079053750</idno>
              <idno type="ORCID">https://orcid.org/0009-0001-6652-9623</idno>
              <affiliation ref="#struct-1041998"/>
              <affiliation ref="#struct-1041968"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Bénédicte</forename>
                <surname>Daly</surname>
              </persName>
              <email type="md5">92327be1433e2922ee854ec5ed0881d7</email>
              <email type="domain">lisn.upsaclay.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-02-20 12:29:24</date>
              <date type="whenModified">2026-03-23 13:45:45</date>
              <date type="whenReleased">2024-02-20 14:30:08</date>
              <date type="whenProduced">2020-12-08</date>
              <date type="whenEndEmbargoed">2024-02-20</date>
              <ref type="file" target="https://hal.science/hal-04468022v1/document">
                <date notBefore="2024-02-20"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-04468022v1/file/2020.coling-main.522.pdf" id="file-4468022-3876804">
                <date notBefore="2024-02-20"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="314321">
                <persName>
                  <forename>Bénédicte</forename>
                  <surname>Daly</surname>
                </persName>
                <email type="md5">92327be1433e2922ee854ec5ed0881d7</email>
                <email type="domain">lisn.upsaclay.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04468022</idno>
            <idno type="halUri">https://hal.science/hal-04468022</idno>
            <idno type="halBibtex">zhai:hal-04468022</idno>
            <idno type="halRefHtml">&lt;i&gt;28th International Conference on Computational Linguistics (COLING)&lt;/i&gt;, Dec 2020, Barcelona (on line), Spain. pp.5944-5956, &lt;a target="_blank" href="https://dx.doi.org/10.18653/v1/2020.coling-main.522"&gt;&amp;#x27E8;10.18653/v1/2020.coling-main.522&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">28th International Conference on Computational Linguistics (COLING), Dec 2020, Barcelona (on line), Spain. pp.5944-5956, &amp;#x27E8;10.18653/v1/2020.coling-main.522&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4468022-3876804"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="LIMSI">Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur</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-ILES" corresp="LISN">Information, Langue Ecrite et Signée </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">Detecting Non-literal Translations by Fine-tuning Cross-lingual Pre-trained Language Models</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Yuming</forename>
                    <surname>Zhai</surname>
                  </persName>
                  <email type="md5">c24b9b87db9aeb09a9a5d6233f97f79c</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">yuming-zhai</idno>
                  <idno type="idhal" notation="numeric">20611</idno>
                  <idno type="halauthorid" notation="string">40422-20611</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3597-2833</idno>
                  <idno type="IDREF">https://www.idref.fr/242113648</idno>
                  <affiliation ref="#struct-1041998"/>
                  <affiliation ref="#struct-1041968"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gabriel</forename>
                    <surname>Illouz</surname>
                  </persName>
                  <email type="md5">e63c74600c9b1282a3609d48a655f6bd</email>
                  <email type="domain">limsi.fr</email>
                  <idno type="idhal" notation="numeric">1053645</idno>
                  <idno type="halauthorid" notation="string">156920-1053645</idno>
                  <idno type="IDREF">https://www.idref.fr/293677522</idno>
                  <affiliation ref="#struct-1041998"/>
                  <affiliation ref="#struct-1041968"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Anne</forename>
                    <surname>Vilnat</surname>
                  </persName>
                  <email type="md5">9ce78ed5537add2d6066d4c3c6fd501e</email>
                  <email type="domain">limsi.fr</email>
                  <idno type="idhal" notation="string">anne-vilnat</idno>
                  <idno type="idhal" notation="numeric">174170</idno>
                  <idno type="halauthorid" notation="string">11967-174170</idno>
                  <idno type="IDREF">https://www.idref.fr/079053750</idno>
                  <idno type="ORCID">https://orcid.org/0009-0001-6652-9623</idno>
                  <affiliation ref="#struct-1041998"/>
                  <affiliation ref="#struct-1041968"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of the 28th International Conference on Computational Linguistics</title>
                <meeting>
                  <title>28th International Conference on Computational Linguistics (COLING)</title>
                  <date type="start">2020-12-08</date>
                  <date type="end">2020-12-13</date>
                  <settlement>Barcelona (on line)</settlement>
                  <country key="ES">Spain</country>
                </meeting>
                <imprint>
                  <publisher>International Committee on Computational Linguistics</publisher>
                  <biblScope unit="pp">5944-5956</biblScope>
                </imprint>
              </monogr>
              <idno type="doi">10.18653/v1/2020.coling-main.522</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</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>Human-generated non-literal translations reflect the richness of human languages and are sometimes indispensable to ensure adequacy and fluency. Non-literal translations are difficult to produce even for human translators, especially for foreign language learners, and machine translations are still on the way to simulate human ones on this aspect. In order to foster the study on appropriate and creative non-literal translations, automatically detecting them in parallel corpora is an important step, which can benefit downstream NLP tasks or help to construct materials to teach translation. This article demonstrates that generic sentence representations produced by a pre-trained cross-lingual language model could be fine-tuned to solve this task. We show that there exists a moderate positive correlation between the prediction probability of being human translation and the non-literal translations' proportion in a sentence. The fine-tuning experiments show an accuracy of 80.16% when predicting the presence of non-literal translations in a sentence and an accuracy of 85.20% when distinguishing literal and non-literal translations at phrase level. We further conduct a linguistic error analysis and propose directions for future work.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1041998" status="OLD">
          <orgName>Information, Langue Ecrite et Signée</orgName>
          <orgName type="acronym">ILES</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2020-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 508, 91405, Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.limsi.fr/fr/recherche/iles</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1041968" type="direct"/>
            <relation active="#struct-419361" type="indirect"/>
            <relation name="UPR3251" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1041968" status="OLD">
          <orgName>Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur</orgName>
          <orgName type="acronym">LIMSI</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2020-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 507, rue du Belvédère,91405, Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.limsi.fr/fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UPR3251" active="#struct-441569" type="direct"/>
          </listRelation>
        </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>
      </listOrg>
    </back>
  </text>
</TEI>