<?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-03890594</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="2026-05-17T04:29:32+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Automatic closed captioning: a study of strategies for televisual genre adaptation</title>
            <title xml:lang="fr">Sous-titrage automatique : étude de stratégies d'adaptation aux genres télévisuels</title>
            <author role="aut">
              <persName>
                <forename type="first">François</forename>
                <surname>Buet</surname>
              </persName>
              <email type="md5">f90223329808f2f1836bd07db749303a</email>
              <email type="domain">mines-nancy.org</email>
              <ptr type="url" target="https://cyossnarf.github.io/"/>
              <idno type="idhal" notation="string">francois-buet</idno>
              <idno type="idhal" notation="numeric">734992</idno>
              <idno type="halauthorid" notation="string">50206-734992</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7405-9182</idno>
              <idno type="IDREF">https://www.idref.fr/266180167</idno>
              <idno type="ARXIV">https://arxiv.org/a/buet_f_1</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=aHarTR8AAAAJ</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>Projet BPI ROSETTA</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-12-08 16:23:07</date>
              <date type="whenModified">2025-03-21 03:15:20</date>
              <date type="whenReleased">2023-01-02 13:19:09</date>
              <date type="whenProduced">2022-12-06</date>
              <date type="whenEndEmbargoed">2022-12-08</date>
              <ref type="file" target="https://hal.science/hal-03890594v1/document">
                <date notBefore="2022-12-08"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-03890594v1/file/TAL_63_1_1_Buet.pdf" id="file-3890594-3404394">
                <date notBefore="2022-12-08"/>
              </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-03890594</idno>
            <idno type="halUri">https://hal.science/hal-03890594</idno>
            <idno type="halBibtex">buet:hal-03890594</idno>
            <idno type="halRefHtml">&lt;i&gt;Revue TAL : traitement automatique des langues&lt;/i&gt;, 2022, Varia, 63 (1), pp.11-35</idno>
            <idno type="halRef">Revue TAL : traitement automatique des langues, 2022, Varia, 63 (1), pp.11-35</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3890594-3404394"/></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="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Automatic closed captioning: a study of strategies for televisual genre adaptation</title>
                <title xml:lang="fr">Sous-titrage automatique : étude de stratégies d'adaptation aux genres télévisuels</title>
                <author role="aut">
                  <persName>
                    <forename type="first">François</forename>
                    <surname>Buet</surname>
                  </persName>
                  <email type="md5">f90223329808f2f1836bd07db749303a</email>
                  <email type="domain">mines-nancy.org</email>
                  <ptr type="url" target="https://cyossnarf.github.io/"/>
                  <idno type="idhal" notation="string">francois-buet</idno>
                  <idno type="idhal" notation="numeric">734992</idno>
                  <idno type="halauthorid" notation="string">50206-734992</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7405-9182</idno>
                  <idno type="IDREF">https://www.idref.fr/266180167</idno>
                  <idno type="ARXIV">https://arxiv.org/a/buet_f_1</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=aHarTR8AAAAJ</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>
                <idno type="halJournalId" status="VALID">62862</idno>
                <idno type="issn">1248-9433</idno>
                <idno type="eissn">1965-0906</idno>
                <title level="j">Revue TAL : traitement automatique des langues</title>
                <imprint>
                  <publisher>Association pour le Traitement Automatique des Langues (ATALA) / Klincksieck</publisher>
                  <biblScope unit="serie">Varia</biblScope>
                  <biblScope unit="volume">63</biblScope>
                  <biblScope unit="issue">1</biblScope>
                  <biblScope unit="pp">11-35</biblScope>
                  <date type="datePub">2022-12-06</date>
                  <date type="dateEpub">2022-12-06</date>
                </imprint>
              </monogr>
              <ref type="publisher">https://www.atala.org/content/tal_63_1_-0</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">machine translation</term>
                <term xml:lang="en">text simplification</term>
                <term xml:lang="en">automatic close captioning</term>
                <term xml:lang="en">automatic close captioning text simplification machine translation</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Interest in automatic closed captioning systems has risen on account of legal obligations concerning accessibility and the sheer amount of audiovisual content being produced by multiple sources. Such systems usually proceed by coupling Automatic Speech Recognition (ASR) and Machine Translation (MT) from transcript to captions. The "translation" task consist of a simplification and segmentation of the text, which must observe norms with respect to display, while handling ASR errors. In the case of TV shows, both the initial audio stream and the target captions vary significantly in form and content according to the program. Taking inspiration in MT literature, this paper implements and compare televisual genre adaptation methods for closed captioning.</p>
            </abstract>
            <abstract xml:lang="fr">
              <p>Les obligations légales concernant l'accessibilité des contenus audiovisuels conjuguées avec l'importance des volumes actuellement produits par diverses sources suscitent un intérêt croissant pour les systèmes de sous-titrage automatique. Traditionnellement, ces systèmes procèdent en enchaînant une étape de reconnaissance de la parole et une étape de « traduction » de la transcription vers les sous-titres. Pour le sous-titrage monolingue, la « traduction » correspond à une simplification et à une segmentation du texte, qui doivent notamment respecter des normes liées à l'affichage, et composer avec les erreurs issues de la reconnaissance vocale. Dans le cas des émissions télévisées, la forme et la teneur du flux audio initial comme des sous-titres à répliquer varient significativement selon les programmes. En prenant inspiration dans la littérature de la traduction automatique, cet article met en place et compare des méthodes d'adaptation aux genres télévisuels pour la production de sous-titres. MOTS-CLÉS : sous-titrage automatique, simplification de textes, traduction automatique.</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>
    </back>
  </text>
</TEI>