<?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-03555255</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="2026-05-17T14:08:45+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">"And cut!" Exploring Textual Representations for Media Content Segmentation and Alignment</title>
            <author role="aut">
              <persName>
                <forename type="first">Ismail</forename>
                <surname>Harrando</surname>
              </persName>
              <email type="md5">ccc949f20300ac83e1fd7804bfdee6bd</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">ismail-harrando</idno>
              <idno type="idhal" notation="numeric">1509824</idno>
              <idno type="halauthorid" notation="string">2131901-1509824</idno>
              <idno type="IDREF">https://www.idref.fr/264165888</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3593-4490</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=eeabWVYAAAAJ</idno>
              <affiliation ref="#struct-421532"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Raphaël</forename>
                <surname>Troncy</surname>
              </persName>
              <email type="md5">e14fa68ad8e76e16dfd996a17513ec23</email>
              <email type="domain">eurecom.fr</email>
              <idno type="idhal" notation="string">raphael-troncy</idno>
              <idno type="idhal" notation="numeric">21317</idno>
              <idno type="halauthorid" notation="string">29079-21317</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=1BxhcigAAAAJ&amp;hl=en</idno>
              <idno type="IDREF">https://www.idref.fr/106969250</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0457-1436</idno>
              <affiliation ref="#struct-421532"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Centre De Documentation</forename>
                <surname>Eurecom</surname>
              </persName>
              <email type="md5">808fb6c747947adf4fb3953c09dd1636</email>
              <email type="domain">eurecom.fr</email>
            </editor>
            <funder ref="#projanr-43551"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-02-03 15:02:18</date>
              <date type="whenModified">2025-02-18 18:28:19</date>
              <date type="whenReleased">2022-02-18 14:44:39</date>
              <date type="whenProduced">2021-06-21</date>
              <date type="whenEndEmbargoed">2022-02-03</date>
              <ref type="file" target="https://hal.science/hal-03555255v1/document">
                <date notBefore="2022-02-03"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03555255v1/file/publi-6539.pdf" id="file-3555255-3111901">
                <date notBefore="2022-02-03"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="118606">
                <persName>
                  <forename>Centre De Documentation</forename>
                  <surname>Eurecom</surname>
                </persName>
                <email type="md5">808fb6c747947adf4fb3953c09dd1636</email>
                <email type="domain">eurecom.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03555255</idno>
            <idno type="halUri">https://hal.science/hal-03555255</idno>
            <idno type="halBibtex">harrando:hal-03555255</idno>
            <idno type="halRefHtml">&lt;i&gt;DataTV-2021, 2nd International Workshop on Data-driven Personalisation of Television&lt;/i&gt;, Jun 2021, Online, France</idno>
            <idno type="halRef">DataTV-2021, 2nd International Workshop on Data-driven Personalisation of Television, Jun 2021, Online, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3555255-3111901"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="EURECOM">EURECOM</idno>
            <idno type="stamp" n="ANR">ANR</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">"And cut!" Exploring Textual Representations for Media Content Segmentation and Alignment</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Ismail</forename>
                    <surname>Harrando</surname>
                  </persName>
                  <email type="md5">ccc949f20300ac83e1fd7804bfdee6bd</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">ismail-harrando</idno>
                  <idno type="idhal" notation="numeric">1509824</idno>
                  <idno type="halauthorid" notation="string">2131901-1509824</idno>
                  <idno type="IDREF">https://www.idref.fr/264165888</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3593-4490</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=eeabWVYAAAAJ</idno>
                  <affiliation ref="#struct-421532"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Raphaël</forename>
                    <surname>Troncy</surname>
                  </persName>
                  <email type="md5">e14fa68ad8e76e16dfd996a17513ec23</email>
                  <email type="domain">eurecom.fr</email>
                  <idno type="idhal" notation="string">raphael-troncy</idno>
                  <idno type="idhal" notation="numeric">21317</idno>
                  <idno type="halauthorid" notation="string">29079-21317</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=1BxhcigAAAAJ&amp;hl=en</idno>
                  <idno type="IDREF">https://www.idref.fr/106969250</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0457-1436</idno>
                  <affiliation ref="#struct-421532"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>DataTV-2021, 2nd International Workshop on Data-driven Personalisation of Television</title>
                  <date type="start">2021-06-21</date>
                  <date type="end">2021-06-23</date>
                  <settlement>Online</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Content Alignment</term>
                <term xml:lang="en">Content segmentation</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ia">Computer Science [cs]/Computer Aided Engineering</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>Text segmentation is a traditional task in NLP where a document is broken down into smaller, coherent segments. While several methods and benchmarks exist for well-formed, and clean textual documents that can be found in long articles or synthetic datasets, segmenting media content comes with different challenges such as the errors produced by the procedure of Automatic Speech Recognition and the lack of sentence end markers that are found in written text (e.g. punctuation marks or HTML tags). Many radio or TV programs are also conversational in nature (e.g. interview and debate), and thus, rely less on repeated words unlike encyclopedia text (e.g. Wikipedia articles) that are frequently used for textual segmentation evaluation. This is even further compounded when working with non-English content. In this work, we present an approach to content segmentation that leverages topical coherence, language modeling and word embeddings to detect change of topics. We evaluate our approach on a real production dataset of French programs that have been manually annotated for segments. We also show how, when a ground truth summary of the content is provided such as segment titles, we can align them to their corresponding segments using the same representations. CCS Concepts: • Computing methodologies → Natural language processing; • Information systems → Content analysis and feature selection.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-421532" status="VALID">
          <orgName>Eurecom [Sophia Antipolis]</orgName>
          <desc>
            <address>
              <addrLine>Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.eurecom.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-43551" status="VALID">
          <idno type="anr">ANR-17-CE38-0010</idno>
          <orgName>ANTRACT</orgName>
          <desc>Analyse Transdisciplinaire des Actualités filmées (1945-1969)</desc>
          <date type="start">2017</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>