<?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-05322834</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="2026-05-26T06:24:45+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Fine-tuning NMT Models and LLMs for Specialised EN-ES Translation Using Aligned Corpora, Glossaries, and Synthetic Data: MULTITAN at WMT25 Terminology Shared Task</title>
            <author role="aut">
              <persName>
                <forename type="first">Lichao</forename>
                <surname>Zhu</surname>
              </persName>
              <email type="md5">3d203558daedc124efb3009029a0f641</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">lichao-zhu</idno>
              <idno type="idhal" notation="numeric">748662</idno>
              <idno type="halauthorid" notation="string">15860-748662</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4432-0236</idno>
              <affiliation ref="#struct-1221485"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Maria</forename>
                <surname>Zimina-Poirot</surname>
              </persName>
              <email type="md5">703580dc38a3b68edc9c75a8f19a0f90</email>
              <email type="domain">u-paris.fr</email>
              <idno type="idhal" notation="string">maria-zimina</idno>
              <idno type="idhal" notation="numeric">4562</idno>
              <idno type="halauthorid" notation="string">1109-4562</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0892-2531</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?hl=en&amp;user=lNkt_lkAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/087626497</idno>
              <affiliation ref="#struct-1221485"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cristian</forename>
                <surname>Valdez</surname>
              </persName>
              <email type="md5">dd73cbf4f2fbd5eee36cd0a4dc748e45</email>
              <email type="domain">u-paris.fr</email>
              <idno type="idhal" notation="string">cristian-valdez</idno>
              <idno type="idhal" notation="numeric">749058</idno>
              <idno type="halauthorid" notation="string">53313-749058</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2291-8085</idno>
              <affiliation ref="#struct-1221485"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Stéphane</forename>
                <surname>Patin</surname>
              </persName>
              <email type="md5">ff97a5b44867d10a3fded8ed6708468a</email>
              <email type="domain">u-paris.fr</email>
              <idno type="idhal" notation="string">patin-stephane</idno>
              <idno type="idhal" notation="numeric">9412</idno>
              <idno type="halauthorid" notation="string">22519-9412</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2568-1191</idno>
              <affiliation ref="#struct-1221485"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Lichao</forename>
                <surname>Zhu</surname>
              </persName>
              <email type="md5">781dfabbf365288bdb0e0412bbc17b79</email>
              <email type="domain">u-paris.fr</email>
            </editor>
            <funder>projet MULTITAN-GML, COPES-2024-12, Université Paris Cité</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-10-20 19:49:17</date>
              <date type="whenModified">2025-11-19 03:14:57</date>
              <date type="whenReleased">2025-11-17 10:13:09</date>
              <date type="whenProduced">2025-11-08</date>
              <date type="whenEndEmbargoed">2025-10-20</date>
              <ref type="file" target="https://hal.science/hal-05322834v1/document">
                <date notBefore="2025-10-20"/>
              </ref>
              <ref type="file" n="1" target="https://hal.science/hal-05322834v1/file/multitan_wmt_2025-20.pdf" id="file-5322834-4591690">
                <date notBefore="2025-10-20"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="192946">
                <persName>
                  <forename>Lichao</forename>
                  <surname>Zhu</surname>
                </persName>
                <email type="md5">781dfabbf365288bdb0e0412bbc17b79</email>
                <email type="domain">u-paris.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05322834</idno>
            <idno type="halUri">https://hal.science/hal-05322834</idno>
            <idno type="halBibtex">zhu:hal-05322834</idno>
            <idno type="halRefHtml">&lt;i&gt;The Tenth Workshop on Machine Translation (WMT)&lt;/i&gt;, ACL, Nov 2025, Suzhou, China. pp.1284-1291</idno>
            <idno type="halRef">The Tenth Workshop on Machine Translation (WMT), ACL, Nov 2025, Suzhou, China. pp.1284-1291</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5322834-4591690"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-PARIS">Université Paris Cité</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS" corresp="UNIV-PARIS">Université Paris Cité</idno>
            <idno type="stamp" n="UP-SOCIETES-HUMANITES">Université Paris Cité - Faculté Sociétés et Humanités</idno>
            <idno type="stamp" n="ALTAE">Approches Linguistiques Théoriques, Appliquées et Expérimentales : langues et cultures connectées</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Fine-tuning NMT Models and LLMs for Specialised EN-ES Translation Using Aligned Corpora, Glossaries, and Synthetic Data: MULTITAN at WMT25 Terminology Shared Task</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Lichao</forename>
                    <surname>Zhu</surname>
                  </persName>
                  <email type="md5">3d203558daedc124efb3009029a0f641</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">lichao-zhu</idno>
                  <idno type="idhal" notation="numeric">748662</idno>
                  <idno type="halauthorid" notation="string">15860-748662</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4432-0236</idno>
                  <affiliation ref="#struct-1221485"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Maria</forename>
                    <surname>Zimina-Poirot</surname>
                  </persName>
                  <email type="md5">703580dc38a3b68edc9c75a8f19a0f90</email>
                  <email type="domain">u-paris.fr</email>
                  <idno type="idhal" notation="string">maria-zimina</idno>
                  <idno type="idhal" notation="numeric">4562</idno>
                  <idno type="halauthorid" notation="string">1109-4562</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0892-2531</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?hl=en&amp;user=lNkt_lkAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/087626497</idno>
                  <affiliation ref="#struct-1221485"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cristian</forename>
                    <surname>Valdez</surname>
                  </persName>
                  <email type="md5">dd73cbf4f2fbd5eee36cd0a4dc748e45</email>
                  <email type="domain">u-paris.fr</email>
                  <idno type="idhal" notation="string">cristian-valdez</idno>
                  <idno type="idhal" notation="numeric">749058</idno>
                  <idno type="halauthorid" notation="string">53313-749058</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2291-8085</idno>
                  <affiliation ref="#struct-1221485"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Stéphane</forename>
                    <surname>Patin</surname>
                  </persName>
                  <email type="md5">ff97a5b44867d10a3fded8ed6708468a</email>
                  <email type="domain">u-paris.fr</email>
                  <idno type="idhal" notation="string">patin-stephane</idno>
                  <idno type="idhal" notation="numeric">9412</idno>
                  <idno type="halauthorid" notation="string">22519-9412</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2568-1191</idno>
                  <affiliation ref="#struct-1221485"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>The Tenth Workshop on Machine Translation (WMT)</title>
                  <date type="start">2025-11-08</date>
                  <date type="end">2025-11-09</date>
                  <settlement>Suzhou</settlement>
                  <country key="CN">China</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>ACL</name>
                </respStmt>
                <imprint>
                  <biblScope unit="pp">1284-1291</biblScope>
                  <date type="datePub">2025-10-06</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">English</term>
                <term xml:lang="en">Terminolgy</term>
                <term xml:lang="en">Textometric Analysis</term>
                <term xml:lang="en">Spanish</term>
                <term xml:lang="en">Fine-tuning multilingual models</term>
                <term xml:lang="en">LLM</term>
                <term xml:lang="en">Machine translation MT</term>
              </keywords>
              <classCode scheme="halDomain" n="scco.ling">Cognitive science/Linguistics</classCode>
              <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 presents a hybrid evaluation of terminology-aware English-to-Spanish machine translation systems developed for the WMT25 Terminology Shared Task, specifically targeting the Information Technology (IT) domain. Our objective was to improve terminology accuracy and overall translation quality and highlight the potential of specialised terminology-aware translation models for technical domains. We used different enhancement strategies for both neural machine translation (NMT) systems and large language models (LLMs). These strategies include fine-tuning with synthetic data, the use of in-domain parallel corpora, and hard constraint methods such as placeholder substitution and in-context glossary integration. The results demonstrate distinct lexical and stylistic profiles in the outputs of fine-tuned NMT systems and LLMs, as well as the complementary advantages of different terminology injection methods. Systems behave differently with and without a glossary, as demonstrated by experimental results. The NMT systems seem to be rather limited in adapting to special lexicons and resizing embeddings, which is the opposite of LLMs, which prefer structured instructions. Although our translation systems achieved their highest scores on the NoTerm, Consistency metrics, exceeding 81%, demonstrating their ability to produce stable and coherent translations of recurring terms and phrases in unconstrained settings, the precision of the terminology and overall quality of the translation could have been improved by additional training.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1221485" status="VALID">
          <idno type="IdRef">12619601X</idno>
          <idno type="RNSR">200515225G</idno>
          <orgName>Approches Linguistiques Théoriques, Appliquées et Expérimentales : langues et cultures connectées</orgName>
          <orgName type="acronym">ALTAE (URP 3967)</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>Campus des Grands Moulins - Bât. Olympe de Gouges, Case postale 7046 - 8 rue Paul Ricoeur, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://clillac-arp.u-paris.fr/</ref>
          </desc>
          <listRelation>
            <relation name="URP 3967" active="#struct-557826" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-557826" status="VALID">
          <idno type="IdRef">236453505</idno>
          <idno type="ISNI">0000 0004 7885 7602</idno>
          <idno type="ROR">https://ror.org/05f82e368</idno>
          <orgName>Université Paris Cité</orgName>
          <orgName type="acronym">UPCité</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>85 boulevard Saint-Germain75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://u-paris.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>