<?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 halshs-00549764</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="2026-05-25T02:48:47+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">The TXM Platform : Building Open-Source Textual Analysis Software Compatible with the TEI Encoding Scheme</title>
            <author role="aut">
              <persName>
                <forename type="first">Serge</forename>
                <surname>Heiden</surname>
              </persName>
              <email type="md5">dc1e0ad3f376e60fdaa2ea7e0a6891ed</email>
              <email type="domain">ens-lyon.fr</email>
              <idno type="idhal" notation="string">serge-heiden</idno>
              <idno type="idhal" notation="numeric">7692</idno>
              <idno type="halauthorid" notation="string">4530-7692</idno>
              <idno type="ISNI">http://isni.org/isni/0000000043807577</idno>
              <idno type="GOOGLE SCHOLAR">cPnHLIgAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/111293383</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4682-7647</idno>
              <affiliation ref="#struct-51028"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Serge</forename>
                <surname>Heiden</surname>
              </persName>
              <email type="md5">dc1e0ad3f376e60fdaa2ea7e0a6891ed</email>
              <email type="domain">ens-lyon.fr</email>
            </editor>
            <funder ref="#projanr-1673"/>
            <funder ref="#projanr-3891"/>
            <funder ref="#projanr-30214"/>
            <funder ref="#projanr-37739"/>
            <funder ref="#projanr-35577"/>
            <funder ref="#projanr-45795"/>
            <funder ref="#projanr-43551"/>
            <funder ref="#projanr-41463"/>
            <funder ref="#projanr-42343"/>
            <funder ref="#projanr-25732"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2010-12-22 15:08:57</date>
              <date type="whenWritten">2009-10-30</date>
              <date type="whenModified">2025-10-13 09:44:14</date>
              <date type="whenReleased">2010-12-31 16:58:18</date>
              <date type="whenProduced">2010-11</date>
              <date type="whenEndEmbargoed">2010-12-22</date>
              <ref type="file" target="https://shs.hal.science/halshs-00549764v1/document">
                <date notBefore="2010-12-22"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://shs.hal.science/halshs-00549764v1/file/paclic24_sheiden.pdf" id="file-549764-516881">
                <date notBefore="2010-12-22"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="114679">
                <persName>
                  <forename>Serge</forename>
                  <surname>Heiden</surname>
                </persName>
                <email type="md5">dc1e0ad3f376e60fdaa2ea7e0a6891ed</email>
                <email type="domain">ens-lyon.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">halshs-00549764</idno>
            <idno type="halUri">https://shs.hal.science/halshs-00549764</idno>
            <idno type="halBibtex">heiden:halshs-00549764</idno>
            <idno type="halRefHtml">&lt;i&gt;24th Pacific Asia Conference on Language, Information and Computation&lt;/i&gt;, Nov 2010, Sendai, Japan. pp.389‑398</idno>
            <idno type="halRef">24th Pacific Asia Conference on Language, Information and Computation, Nov 2010, Sendai, Japan. pp.389‑398</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-549764-516881"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SHS">Sciences de l'Homme et de la Société</idno>
            <idno type="stamp" n="ENS-LYON">École Normale Supérieure de Lyon</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-LYON2">Université Lumière Lyon 2</idno>
            <idno type="stamp" n="ENS-LSH">Ecole Normale Supérieure Lettres et Sciences Humaines</idno>
            <idno type="stamp" n="PRUNEL">Ecole Normale Supérieure de Lyon</idno>
            <idno type="stamp" n="AO-LINGUISTIQUE">Archives ouvertes de la Linguistique</idno>
            <idno type="stamp" n="ICAR" corresp="SHS">Interactions, Corpus, Apprentissages, Représentations</idno>
            <idno type="stamp" n="DEMOCRAT">Publications du projet ANR Democrat</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="MATRICE-13NOV">Programmes ANR "Matrice" et "13 Novembre"</idno>
            <idno type="stamp" n="MATRICE" corresp="MATRICE-13NOV">Programme MATRICE</idno>
            <idno type="stamp" n="HAL-LYON-2-NOUVELLE-VERSION">Nouvelle version portail </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">The TXM Platform : Building Open-Source Textual Analysis Software Compatible with the TEI Encoding Scheme</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Serge</forename>
                    <surname>Heiden</surname>
                  </persName>
                  <email type="md5">dc1e0ad3f376e60fdaa2ea7e0a6891ed</email>
                  <email type="domain">ens-lyon.fr</email>
                  <idno type="idhal" notation="string">serge-heiden</idno>
                  <idno type="idhal" notation="numeric">7692</idno>
                  <idno type="halauthorid" notation="string">4530-7692</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000043807577</idno>
                  <idno type="GOOGLE SCHOLAR">cPnHLIgAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/111293383</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4682-7647</idno>
                  <affiliation ref="#struct-51028"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Statistical Analysis of Textual Data - Proceedings of 10th International Conference Journées d'Analyse statistique des Données Textuelles</title>
                <meeting>
                  <title>24th Pacific Asia Conference on Language, Information and Computation</title>
                  <date type="start">2010-11</date>
                  <date type="end">2010-11</date>
                  <settlement>Sendai</settlement>
                  <country key="JP">Japan</country>
                </meeting>
                <editor>R. Otoguro</editor>
                <editor>K. Yoshimoto</editor>
                <editor>K. Ishikawa</editor>
                <editor>H. Umemoto</editor>
                <editor>&amp; Y. Harada</editor>
                <imprint>
                  <publisher>Institute for Digital Enhancement of Cognitive Development, Waseda University</publisher>
                  <biblScope unit="volume">2</biblScope>
                  <biblScope unit="issue">3</biblScope>
                  <biblScope unit="pp">389‑398</biblScope>
                  <date type="datePub">2010-06-09</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">search engine</term>
                <term xml:lang="en">statistical analysis</term>
                <term xml:lang="en">xml-tei corpora</term>
                <term xml:lang="en">open-source</term>
                <term xml:lang="en">textometry</term>
              </keywords>
              <classCode scheme="halDomain" n="shs.stat">Humanities and Social Sciences/Methods and statistics</classCode>
              <classCode scheme="halDomain" n="shs.langue">Humanities and Social Sciences/Linguistics</classCode>
              <classCode scheme="halDomain" n="info.info-dl">Computer Science [cs]/Digital Libraries [cs.DL]</classCode>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</classCode>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</classCode>
              <classCode scheme="halDomain" n="stat.ap">Statistics [stat]/Applications [stat.AP]</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>Abstract. This paper describes the rationale and design of an XML-TEI encoded corpora compatible analysis platform for text mining called TXM.The design of this platform is based on a synthesis of the best available algorithms in existing textometry software. It also relies on identifying the most relevant open-source technologies for processing textual resources encoded in XML and Unicode, for efficient full-text search on annotated corpora and for statistical data analysis.The architecture is based on a Java toolbox articulating a full-text search engine component with a statistical computing environment and with an original import environment able to process a large variety of data sources, including XML-TEI, and to apply embedded NLP tools to them.The platform is distributed as an open-source Eclipse project for developers and in the form of two demonstrator applications for end users: a standard application to install on a workstation and an online web application framework.</p>
            </abstract>
            <particDesc>
              <org type="consortium">Les auteurs remercient le LABEX ASLAN (ANR-10-LABX-0081) de l'Université de Lyon pour son soutien financier dans le cadre du programme "Investissements d'Avenir" (ANR-11-IDEX-0007) de l'Etat Français géré par l'Agence Nationale de la Recherche (ANR).</org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-51028" status="VALID">
          <idno type="IdRef">080671594</idno>
          <idno type="RNSR">200311862K</idno>
          <idno type="ROR">https://ror.org/04mn0nr69</idno>
          <orgName>Interactions, Corpus, Apprentissages, Représentations</orgName>
          <orgName type="acronym">ICAR</orgName>
          <date type="start">2003-01-01</date>
          <desc>
            <address>
              <addrLine>Adresse principale : École Normale Supérieure de Lyon – Site Descartes15, Parvis René DescartesBP 700069342 LYON cedex 07/ Site de Lyon 2 : Université Lumière Lyon25, av. Pierre Mendès-FranceCP 1169676 BRON Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://icar.cnrs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-6818" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-33804" type="direct"/>
            <relation name="UMR5191" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-6818" status="VALID">
          <idno type="IdRef">149154992</idno>
          <idno type="ISNI">0000000123319856</idno>
          <idno type="ROR">https://ror.org/04zmssz18</idno>
          <idno type="Wikidata">Q10159</idno>
          <orgName>École normale supérieure de Lyon</orgName>
          <orgName type="acronym">ENS de Lyon</orgName>
          <date type="start">2010-01-01</date>
          <desc>
            <address>
              <addrLine>15 parvis René Descartes - BP 7000 - 69342 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ens-lyon.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="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="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>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-1673" status="VALID">
          <idno type="anr">ANR-06-CORP-0029</idno>
          <idno type="program">Corpus et outils de la recherche en sciences humaines et sociales</idno>
          <orgName>TEXTOMETRIE</orgName>
          <desc>Fédération des recherches et développements en textométrie autour de la création d'une plateforme logicielle ouverte</desc>
          <date type="start">2006</date>
        </org>
        <org type="anrProject" xml:id="projanr-3891" status="VALID">
          <idno type="anr">ANR-07-CORP-0015</idno>
          <idno type="program">Corpus et outils de la recherche en sciences humaines et sociales</idno>
          <orgName>CORPTEF</orgName>
          <desc>Corpus représentatif des premiers textes français</desc>
          <date type="start">2007</date>
        </org>
        <org type="anrProject" xml:id="projanr-30214" status="VALID">
          <idno type="anr">ANR-08-FRAL-0006</idno>
          <idno type="program">AAP franco-allemand</idno>
          <orgName>SRCMF</orgName>
          <desc>Corpus syntaxique de référence pour le français médiéval</desc>
          <date type="start">2008</date>
        </org>
        <org type="anrProject" xml:id="projanr-37739" status="VALID">
          <idno type="anr">ANR-10-EQPX-0021</idno>
          <idno type="program">Equipements d'excellence</idno>
          <orgName>MATRICE_ANR</orgName>
          <desc>Outils de recherche pour l'analyse de la mémoire par la coopération internationale et les expérimentations. Entre mémoire individuelle et mémoire sociale: les outils et nécessités de l'innovation</desc>
          <date type="start">2010</date>
        </org>
        <org type="anrProject" xml:id="projanr-35577" status="VALID">
          <idno type="anr">ANR-12-CORP-0010</idno>
          <idno type="program">Corpus, données et outils de la recherche en sciences humaines et sociales</idno>
          <orgName>ORIFLAMMS</orgName>
          <desc>Recherche en ontologie, Descripteurs d'images, Analyse des formes et lettres des écritures médiévales multilingues</desc>
          <date type="start">2012</date>
        </org>
        <org type="anrProject" xml:id="projanr-45795" status="VALID">
          <idno type="anr">ANR-15-CE38-0008</idno>
          <orgName>DEMOCRAT</orgName>
          <desc>DEscription et MOdélisation des Chaînes de Référence : outils pour l'Annotation de corpus (en diachronie et en langues comparées) et le Traitement automatique</desc>
          <date type="start">2015</date>
        </org>
        <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>
        <org type="anrProject" xml:id="projanr-41463" status="VALID">
          <idno type="anr">ANR-14-FRAL-0006</idno>
          <idno type="program">Programme franco-allemand en Sciences humaines et sociales</idno>
          <orgName>PaLaFra</orgName>
          <desc>Le PAssage du LAtin au FRAnçais: constitution et analyse d'un corpus numérique latino-français</desc>
          <date type="start">2014</date>
        </org>
        <org type="anrProject" xml:id="projanr-42343" status="VALID">
          <idno type="anr">ANR-16-CE38-0010</idno>
          <orgName>PROFITEROLE</orgName>
          <desc>Modélisation de l'évolution de la langue à partir de textes d'ancien français instrumentés</desc>
          <date type="start">2016</date>
        </org>
        <org type="anrProject" xml:id="projanr-25732" status="VALID">
          <idno type="anr">ANR-11-IDEX-0007</idno>
          <orgName>Avenir L.S.E.</orgName>
          <desc>PROJET AVENIR LYON SAINT-ETIENNE</desc>
          <date type="start">2011</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>