<?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-02552437</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="2026-05-09T16:19:32+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A meaningful information extraction system for interactive analysis of documents</title>
            <author role="aut">
              <persName>
                <forename type="first">Julien</forename>
                <surname>Maitre</surname>
              </persName>
              <email type="md5">6b59fe0ee56a5457f7b0e3c2cdc0ee20</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="string">julienmaitre</idno>
              <idno type="idhal" notation="numeric">184234</idno>
              <idno type="halauthorid" notation="string">42845-184234</idno>
              <idno type="IDREF">https://www.idref.fr/267371969</idno>
              <affiliation ref="#struct-40831"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Michel</forename>
                <surname>Ménard</surname>
              </persName>
              <email type="md5">8a5b458753c652c55a93ad6089303337</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="numeric">865566</idno>
              <idno type="halauthorid" notation="string">264780-865566</idno>
              <affiliation ref="#struct-40831"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Guillaume</forename>
                <surname>Chiron</surname>
              </persName>
              <email type="md5">53df06c648db3952c60305987a802f7b</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="string">guillaume-chiron</idno>
              <idno type="idhal" notation="numeric">744676</idno>
              <idno type="halauthorid" notation="string">18170-744676</idno>
              <idno type="IDREF">https://www.idref.fr/189106689</idno>
              <affiliation ref="#struct-40831"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Alain</forename>
                <surname>Bouju</surname>
              </persName>
              <email type="md5">5e76ca9ae00af4a246354a814bc81c3e</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="string">alain-bouju</idno>
              <idno type="idhal" notation="numeric">740745</idno>
              <idno type="halauthorid" notation="string">379199-740745</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1599-9326</idno>
              <idno type="IDREF">https://www.idref.fr/092855997</idno>
              <affiliation ref="#struct-40831"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nicolas</forename>
                <surname>Sidère</surname>
              </persName>
              <email type="md5">c4df97f37264df4381a1afabc85d28f3</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="string">nsidere</idno>
              <idno type="idhal" notation="numeric">9116</idno>
              <idno type="halauthorid" notation="string">7646-9116</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6719-5007</idno>
              <idno type="IDREF">https://www.idref.fr/172574358</idno>
              <affiliation ref="#struct-40831"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Julien</forename>
                <surname>Maitre</surname>
              </persName>
              <email type="md5">6b59fe0ee56a5457f7b0e3c2cdc0ee20</email>
              <email type="domain">univ-lr.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-04-23 15:53:37</date>
              <date type="whenModified">2024-12-06 10:42:02</date>
              <date type="whenReleased">2020-05-07 13:08:42</date>
              <date type="whenProduced">2019-09-20</date>
              <date type="whenEndEmbargoed">2020-04-23</date>
              <ref type="file" target="https://hal.science/hal-02552437v1/document">
                <date notBefore="2020-04-23"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02552437v1/file/PID6008627.pdf" id="file-2552437-2419389">
                <date notBefore="2020-04-23"/>
              </ref>
              <ref type="externalLink" target="https://hal.archives-ouvertes.fr/hal-02552437/file/PID6008627.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="489246">
                <persName>
                  <forename>Julien</forename>
                  <surname>Maitre</surname>
                </persName>
                <email type="md5">6b59fe0ee56a5457f7b0e3c2cdc0ee20</email>
                <email type="domain">univ-lr.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02552437</idno>
            <idno type="halUri">https://hal.science/hal-02552437</idno>
            <idno type="halBibtex">maitre:hal-02552437</idno>
            <idno type="halRefHtml">&lt;i&gt;International Conference on Document Analysis and Recognition (ICDAR 2019)&lt;/i&gt;, Sep 2019, Sydney, Australia. pp.92-99, &lt;a target="_blank" href="https://dx.doi.org/10.1109/ICDAR.2019.00024"&gt;&amp;#x27E8;10.1109/ICDAR.2019.00024&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">International Conference on Document Analysis and Recognition (ICDAR 2019), Sep 2019, Sydney, Australia. pp.92-99, &amp;#x27E8;10.1109/ICDAR.2019.00024&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2552437-2419389"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="L3I">Laboratoire Informatique, Image et Interaction</idno>
            <idno type="stamp" n="UNIV-ROCHELLE">Université de La Rochelle</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">A meaningful information extraction system for interactive analysis of documents</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Julien</forename>
                    <surname>Maitre</surname>
                  </persName>
                  <email type="md5">6b59fe0ee56a5457f7b0e3c2cdc0ee20</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="string">julienmaitre</idno>
                  <idno type="idhal" notation="numeric">184234</idno>
                  <idno type="halauthorid" notation="string">42845-184234</idno>
                  <idno type="IDREF">https://www.idref.fr/267371969</idno>
                  <affiliation ref="#struct-40831"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Michel</forename>
                    <surname>Ménard</surname>
                  </persName>
                  <email type="md5">8a5b458753c652c55a93ad6089303337</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="numeric">865566</idno>
                  <idno type="halauthorid" notation="string">264780-865566</idno>
                  <affiliation ref="#struct-40831"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Guillaume</forename>
                    <surname>Chiron</surname>
                  </persName>
                  <email type="md5">53df06c648db3952c60305987a802f7b</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="string">guillaume-chiron</idno>
                  <idno type="idhal" notation="numeric">744676</idno>
                  <idno type="halauthorid" notation="string">18170-744676</idno>
                  <idno type="IDREF">https://www.idref.fr/189106689</idno>
                  <affiliation ref="#struct-40831"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Alain</forename>
                    <surname>Bouju</surname>
                  </persName>
                  <email type="md5">5e76ca9ae00af4a246354a814bc81c3e</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="string">alain-bouju</idno>
                  <idno type="idhal" notation="numeric">740745</idno>
                  <idno type="halauthorid" notation="string">379199-740745</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1599-9326</idno>
                  <idno type="IDREF">https://www.idref.fr/092855997</idno>
                  <affiliation ref="#struct-40831"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nicolas</forename>
                    <surname>Sidère</surname>
                  </persName>
                  <email type="md5">c4df97f37264df4381a1afabc85d28f3</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="string">nsidere</idno>
                  <idno type="idhal" notation="numeric">9116</idno>
                  <idno type="halauthorid" notation="string">7646-9116</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6719-5007</idno>
                  <idno type="IDREF">https://www.idref.fr/172574358</idno>
                  <affiliation ref="#struct-40831"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>International Conference on Document Analysis and Recognition (ICDAR 2019)</title>
                  <date type="start">2019-09-20</date>
                  <settlement>Sydney</settlement>
                  <country key="AU">Australia</country>
                </meeting>
                <imprint>
                  <biblScope unit="serie">2019 International Conference on Document Analysis and Recognition (ICDAR)</biblScope>
                  <biblScope unit="pp">92-99</biblScope>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/ICDAR.2019.00024</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Weak signals</term>
                <term xml:lang="en">Vizualisation</term>
                <term xml:lang="en">Multi-agent systems</term>
                <term xml:lang="en">Word embeddings</term>
                <term xml:lang="en">Clustering topics</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</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 is related to a project aiming at discovering weak signals from different streams of information, possibly sent by whistleblowers. The study presented in this paper tackles the particular problem of clustering topics at multi-levels from multiple documents, and then extracting meaningful descriptors, such as weighted lists of words for document representations in a multi-dimensions space. In this context, we present a novel idea which combines Latent Dirichlet Allocation and Word2vec (providing a consistency metric regarding the partitioned topics) as potential method for limiting the "a priori" number of cluster K usually needed in classical partitioning approaches. We proposed 2 implementations of this idea, respectively able to: (1) finding the best K for LDA in terms of topic consistency; (2) gathering the optimal clusters from different levels of clustering. We also proposed a non-traditional visualization approach based on a multi-agents system which combines both dimension reduction and interactivity.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-40831" status="VALID">
          <idno type="IdRef">183449045</idno>
          <idno type="RNSR">199613735B</idno>
          <idno type="ROR">https://ror.org/03r7r0k94</idno>
          <orgName>Laboratoire Informatique, Image et Interaction - EA 2118</orgName>
          <orgName type="acronym">L3I</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://l3i.univ-larochelle.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA2118" active="#struct-300311" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300311" status="VALID">
          <idno type="IdRef">035375043</idno>
          <idno type="ISNI">0000 0001 2169 7335</idno>
          <idno type="ROR">https://ror.org/04mv1z119</idno>
          <orgName>La Rochelle Université</orgName>
          <orgName type="acronym">ULR</orgName>
          <desc>
            <address>
              <addrLine>Technoforum - 23 avenue Albert Einstein - BP 33060 - 17031 La Rochelle - France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-larochelle.fr</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>