<?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-02115294v3</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="2026-05-09T04:27:58+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Textual data summarization using the Self-Organized Co-Clustering model</title>
            <author role="aut">
              <persName>
                <forename type="first">Margot</forename>
                <surname>Selosse</surname>
              </persName>
              <email type="md5">a14effc04d90b2a7e256d805ef98f2d8</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">1386825</idno>
              <idno type="halauthorid" notation="string">1265225-1386825</idno>
              <idno type="IDREF">https://www.idref.fr/278417361</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1422-688X</idno>
              <affiliation ref="#struct-183072"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Julien</forename>
                <surname>Jacques</surname>
              </persName>
              <email type="md5">0aa98b5d47aa9c4fa0e1bf04c4d413c1</email>
              <email type="domain">univ-lyon2.fr</email>
              <idno type="idhal" notation="string">julien-jacques</idno>
              <idno type="idhal" notation="numeric">173226</idno>
              <idno type="halauthorid" notation="string">31247-173226</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4808-2781</idno>
              <idno type="GOOGLE SCHOLAR">wD9lj5MAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/098191551</idno>
              <affiliation ref="#struct-183072"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Christophe</forename>
                <surname>Biernacki</surname>
              </persName>
              <email type="md5">43e0441de674b54b1fdadd08d3f2451a</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="numeric">923939</idno>
              <idno type="halauthorid" notation="string">142378-923939</idno>
              <affiliation ref="#struct-128611"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Margot</forename>
                <surname>Selosse</surname>
              </persName>
              <email type="md5">a14effc04d90b2a7e256d805ef98f2d8</email>
              <email type="domain">gmail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2019-04-30 10:53:00</date>
            </edition>
            <edition n="v2">
              <date type="whenSubmitted">2019-12-09 12:01:10</date>
            </edition>
            <edition n="v3" type="current">
              <date type="whenSubmitted">2020-02-24 18:27:34</date>
              <date type="whenModified">2025-11-20 11:53:18</date>
              <date type="whenReleased">2020-03-06 09:48:17</date>
              <date type="whenProduced">2020-02</date>
              <date type="whenEndEmbargoed">2020-02-24</date>
              <ref type="file" target="https://hal.science/hal-02115294v3/document">
                <date notBefore="2020-02-24"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02115294v3/file/manuscript.pdf" id="file-2490025-2365633">
                <date notBefore="2020-02-24"/>
              </ref>
              <ref type="externalLink" target="https://hal.archives-ouvertes.fr/hal-02115294/file/manuscript.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="571639">
                <persName>
                  <forename>Margot</forename>
                  <surname>Selosse</surname>
                </persName>
                <email type="md5">a14effc04d90b2a7e256d805ef98f2d8</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02115294</idno>
            <idno type="halUri">https://hal.science/hal-02115294</idno>
            <idno type="halBibtex">selosse:hal-02115294</idno>
            <idno type="halRefHtml">&lt;i&gt;Pattern Recognition&lt;/i&gt;, 2020, 103, pp.107315. &lt;a target="_blank" href="https://dx.doi.org/10.1016/j.patcog.2020.107315"&gt;&amp;#x27E8;10.1016/j.patcog.2020.107315&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Pattern Recognition, 2020, 103, pp.107315. &amp;#x27E8;10.1016/j.patcog.2020.107315&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2490025-2365633"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="UNIV-LYON1">Université Claude Bernard - Lyon I</idno>
            <idno type="stamp" n="UNIV-LYON2">Université Lumière Lyon 2</idno>
            <idno type="stamp" n="INRIA-LILLE">INRIA Lille - Nord Europe</idno>
            <idno type="stamp" n="INSMI">CNRS-INSMI - INstitut des Sciences Mathématiques et de leurs Interactions</idno>
            <idno type="stamp" n="ERIC" corresp="UNIV-LYON2">Equipe de Recherche en Ingénierie des Connaissances</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="LYON2">Université Lyon2</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="INRIAARTDOI">INRIAARTDOI</idno>
            <idno type="stamp" n="LPP-MATH">Laboratoire Paul Painlevé (UMR8524)</idno>
            <idno type="stamp" n="AILYS">AILys</idno>
            <idno type="stamp" n="HAL-LYON-2-NOUVELLE-VERSION">Nouvelle version portail </idno>
            <idno type="stamp" n="METRICS">Evaluation des technologies de santé et des pratiques médicales</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">Textual data summarization using the Self-Organized Co-Clustering model</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Margot</forename>
                    <surname>Selosse</surname>
                  </persName>
                  <email type="md5">a14effc04d90b2a7e256d805ef98f2d8</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">1386825</idno>
                  <idno type="halauthorid" notation="string">1265225-1386825</idno>
                  <idno type="IDREF">https://www.idref.fr/278417361</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1422-688X</idno>
                  <affiliation ref="#struct-183072"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Julien</forename>
                    <surname>Jacques</surname>
                  </persName>
                  <email type="md5">0aa98b5d47aa9c4fa0e1bf04c4d413c1</email>
                  <email type="domain">univ-lyon2.fr</email>
                  <idno type="idhal" notation="string">julien-jacques</idno>
                  <idno type="idhal" notation="numeric">173226</idno>
                  <idno type="halauthorid" notation="string">31247-173226</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4808-2781</idno>
                  <idno type="GOOGLE SCHOLAR">wD9lj5MAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/098191551</idno>
                  <affiliation ref="#struct-183072"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Christophe</forename>
                    <surname>Biernacki</surname>
                  </persName>
                  <email type="md5">43e0441de674b54b1fdadd08d3f2451a</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="numeric">923939</idno>
                  <idno type="halauthorid" notation="string">142378-923939</idno>
                  <affiliation ref="#struct-128611"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">17798</idno>
                <idno type="issn">0031-3203</idno>
                <title level="j">Pattern Recognition</title>
                <imprint>
                  <publisher>Elsevier</publisher>
                  <biblScope unit="volume">103</biblScope>
                  <biblScope unit="pp">107315</biblScope>
                  <date type="datePub">2020-02</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1016/j.patcog.2020.107315</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">coclustering</term>
                <term xml:lang="en">Latent Block Model</term>
                <term xml:lang="en">document-term matrix</term>
              </keywords>
              <classCode scheme="halDomain" n="math.math-st">Mathematics [math]/Statistics [math.ST]</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>Recently, different studies have demonstrated the use of co-clustering, a data mining technique which simultaneously produces row-clusters of observations and column-clusters of features. The present work introduces a novel co-clustering model to easily summarize textual data in a document-term format. In addition to highlighting homogeneous co-clusters as other existing algorithms do we also distinguish noisy co-clusters from significant co-clusters, which is particularly useful for sparse document-term matrices. Furthermore, our model proposes a structure among the significant co-clusters, thus providing improved interpretability to users. The approach proposed contends with state-of-the-art methods for document and term clustering and offers user-friendly results. The model relies on the Poisson distribution and on a constrained version of the Latent Block Model, which is a probabilistic approach for co-clustering. A Stochastic Expectation-Maximization algorithm is proposed to run the model’s inference as well as a model selection criterion to choose the number of coclusters. Both simulated and real data sets illustrate the eciency of this model by its ability to easily identify relevant co-clusters.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-183072" status="VALID">
          <idno type="IdRef">168642174</idno>
          <idno type="RNSR">199914397H</idno>
          <idno type="ROR">https://ror.org/009frb846</idno>
          <orgName>Entrepôts, Représentation et Ingénierie des Connaissances</orgName>
          <orgName type="acronym">ERIC</orgName>
          <desc>
            <address>
              <addrLine>Université Lumière Lyon 2 5 avenue Pierre Mendès-France 69676 Bron Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://eric.univ-lyon2.fr</ref>
          </desc>
          <listRelation>
            <relation name="EA3083" active="#struct-33804" type="direct"/>
            <relation active="#struct-194495" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-128611" status="OLD">
          <idno type="RNSR">201020969D</idno>
          <idno type="ROR">https://ror.org/05sk9zb20</idno>
          <orgName>MOdel for Data Analysis and Learning</orgName>
          <orgName type="acronym">MODAL</orgName>
          <date type="start">2010-09-01</date>
          <date type="end">2025-07-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/modal</ref>
          </desc>
          <listRelation>
            <relation active="#struct-32" type="direct"/>
            <relation name="UMR8524" active="#struct-374570" type="indirect"/>
            <relation name="UMR8524" active="#struct-441569" type="indirect"/>
            <relation active="#struct-92973" type="direct"/>
            <relation active="#struct-104752" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-221576" type="direct"/>
            <relation name="ULR2694" active="#struct-374570" type="indirect"/>
            <relation name="ULR2694" active="#struct-425779" type="indirect"/>
            <relation active="#struct-355607" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-33804" status="VALID">
          <idno type="IdRef">02640334X</idno>
          <idno type="ISNI">0000 0001 2188 0906</idno>
          <idno type="ROR">https://ror.org/03rth4p18</idno>
          <idno type="Wikidata">Q4041</idno>
          <orgName>Université Lumière - Lyon 2</orgName>
          <orgName type="acronym">UL2</orgName>
          <desc>
            <address>
              <addrLine>86, rue Pasteur - 69007 Lyon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon2.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-194495" status="VALID">
          <idno type="IdRef">026402823</idno>
          <idno type="ISNI">0000000121686185</idno>
          <idno type="ROR">https://ror.org/029brtt94</idno>
          <orgName>Université Claude Bernard Lyon 1</orgName>
          <orgName type="acronym">UCBL</orgName>
          <desc>
            <address>
              <addrLine>43, boulevard du 11 novembre 1918, 69622 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301088" status="VALID">
          <idno type="ROR">https://ror.org/01rk35k63</idno>
          <orgName>Université de Lyon</orgName>
          <desc>
            <address>
              <addrLine>92 rue Pasteur - CS 30122, 69361 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-lyon.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-32" status="VALID">
          <idno type="IdRef">161603971</idno>
          <idno type="ISNI">0000000403684081</idno>
          <idno type="RNSR">199812852H</idno>
          <idno type="ROR">https://ror.org/043n4fm24</idno>
          <idno type="Wikidata">Q3214464</idno>
          <orgName>Laboratoire Paul Painlevé - UMR 8524</orgName>
          <orgName type="acronym">LPP</orgName>
          <date type="start">2004-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Sciences et technologies - U.F.R. de Mathématiques - 59655 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://math.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR8524" active="#struct-374570" type="direct"/>
            <relation name="UMR8524" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-374570" status="VALID">
          <idno type="IdRef">223446556</idno>
          <idno type="ISNI">0000 0001 2242 6780</idno>
          <idno type="ROR">https://ror.org/02kzqn938</idno>
          <idno type="Wikidata">Q3551621</idno>
          <orgName>Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>EPE Université de Lille. -- 42 rue Paul Duez, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lille.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="institution" xml:id="struct-92973" status="OLD">
          <idno type="IdRef">026404184</idno>
          <idno type="ROR">https://ror.org/0546v5182</idno>
          <orgName>Université de Lille, Sciences et Technologies</orgName>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>Cité Scientifique - 59655 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lille1.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-104752" status="VALID">
          <idno type="RNSR">200818245B</idno>
          <idno type="ROR">https://ror.org/04eej9726</idno>
          <orgName>Centre Inria de l'Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>Parc Scientifique de la Haute Borne 40, avenue Halley Bât.A, Park Plaza 59650 Villeneuve d'Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/lille/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" 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="laboratory" xml:id="struct-221576" status="VALID">
          <idno type="IdRef">191047686</idno>
          <idno type="RNSR">199814198W</idno>
          <idno type="ROR">https://ror.org/01qygwc68</idno>
          <idno type="Wikidata">Q116959515</idno>
          <orgName>Evaluation des technologies de santé et des pratiques médicales - ULR 2694</orgName>
          <orgName type="acronym">METRICS</orgName>
          <date type="start">1998-01-01</date>
          <desc>
            <address>
              <addrLine>1, place de Verdun 59045 - Lille cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://metrics.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="ULR2694" active="#struct-374570" type="direct"/>
            <relation name="ULR2694" active="#struct-425779" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-425779" status="VALID">
          <idno type="IdRef">034424636</idno>
          <idno type="ISNI">0000000404718845</idno>
          <idno type="ROR">https://ror.org/02ppyfa04</idno>
          <idno type="Wikidata">Q2945741</idno>
          <orgName>Centre Hospitalier Régional Universitaire [CHU Lille]</orgName>
          <orgName type="acronym">CHRU Lille</orgName>
          <desc>
            <address>
              <addrLine>CHU/CHRU Lille - 2, avenue Oscar Lambret - 59037 Lille Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.chru-lille.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-355607" status="VALID">
          <idno type="ISNI">0000000406406108</idno>
          <orgName>École polytechnique universitaire de Lille</orgName>
          <orgName type="acronym">Polytech Lille</orgName>
          <date type="start">2002-04-04</date>
          <desc>
            <address>
              <addrLine>- Avenue Paul Langevin- 59655 Villeneuve d'Ascq cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.polytech-lille.fr/ecole-d-ingenieurs.html</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>