<?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-00467951</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="2026-05-06T15:41:04+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">POS-tagging for Oral Texts with CRF and Category Decomposition</title>
            <author role="aut">
              <persName>
                <forename type="first">Isabelle</forename>
                <surname>Tellier</surname>
              </persName>
              <email type="md5">643dcf728d91b3023b309a60a32f4ff8</email>
              <email type="domain">sorbonne-nouvelle.fr</email>
              <idno type="idhal" notation="string">isabelle-tellier</idno>
              <idno type="idhal" notation="numeric">10815</idno>
              <idno type="halauthorid" notation="string">3552-10815</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0977-2926</idno>
              <idno type="IDREF">https://www.idref.fr/154913634</idno>
              <affiliation ref="#struct-1625"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Iris</forename>
                <surname>Eshkol</surname>
              </persName>
              <email type="md5">7924056b460473adb79b923b51531c99</email>
              <email type="domain">parisnanterre.fr</email>
              <idno type="idhal" notation="string">iris-eshkol-taravella</idno>
              <idno type="idhal" notation="numeric">18520</idno>
              <idno type="halauthorid" notation="string">194454-18520</idno>
              <idno type="IDREF">https://www.idref.fr/074195158</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0814-3623</idno>
              <affiliation ref="#struct-16494"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Samer</forename>
                <surname>Taalab</surname>
              </persName>
              <idno type="halauthorid">445274-0</idno>
              <affiliation ref="#struct-1625"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jean-Philippe</forename>
                <surname>Prost</surname>
              </persName>
              <email type="md5">6bfbf10058b33ad912f15f9f9d513006</email>
              <email type="domain">univ-amu.fr</email>
              <idno type="idhal" notation="string">jean-philippe-prost</idno>
              <idno type="idhal" notation="numeric">13248</idno>
              <idno type="halauthorid" notation="string">18272-13248</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2804-9191</idno>
              <idno type="IDREF">https://www.idref.fr/146636635</idno>
              <affiliation ref="#struct-1625"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Jean-Philippe</forename>
                <surname>Prost</surname>
              </persName>
              <email type="md5">6bfbf10058b33ad912f15f9f9d513006</email>
              <email type="domain">univ-amu.fr</email>
            </editor>
            <funder ref="#projanr-4075"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2010-03-29 16:12:43</date>
              <date type="whenWritten">2010-01</date>
              <date type="whenModified">2025-08-12 15:29:43</date>
              <date type="whenReleased">2010-03-30 08:32:57</date>
              <date type="whenProduced">2010-03</date>
              <date type="whenEndEmbargoed">2010-03-29</date>
              <ref type="file" target="https://hal.science/hal-00467951v1/document">
                <date notBefore="2010-03-29"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-00467951v1/file/tellierEtAl2010-cicling.pdf" id="file-467951-530848">
                <date notBefore="2010-03-29"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="135851">
                <persName>
                  <forename>Jean-Philippe</forename>
                  <surname>Prost</surname>
                </persName>
                <email type="md5">6bfbf10058b33ad912f15f9f9d513006</email>
                <email type="domain">univ-amu.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00467951</idno>
            <idno type="halUri">https://hal.science/hal-00467951</idno>
            <idno type="halBibtex">tellier:hal-00467951</idno>
            <idno type="halRefHtml">&lt;i&gt;Research in Computing Science&lt;/i&gt;, 2010, 46, pp.79--90</idno>
            <idno type="halRef">Research in Computing Science, 2010, 46, pp.79--90</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-467951-530848"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-ORLEANS">Université d'Orléans</idno>
            <idno type="stamp" n="ENSI-BOURGES">Ecole Nationale Supérieure d'Ingénieurs de Bourges</idno>
            <idno type="stamp" n="CASCIMODOT">CaSciModOT (calcul scientifique et modelisation Orleans-Tours)</idno>
            <idno type="stamp" n="MSL">Modelisation Systemes Langages</idno>
            <idno type="stamp" n="MSL-THESE">Modelisation Systemes Langages</idno>
            <idno type="stamp" n="ANR">ANR</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">POS-tagging for Oral Texts with CRF and Category Decomposition</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Isabelle</forename>
                    <surname>Tellier</surname>
                  </persName>
                  <email type="md5">643dcf728d91b3023b309a60a32f4ff8</email>
                  <email type="domain">sorbonne-nouvelle.fr</email>
                  <idno type="idhal" notation="string">isabelle-tellier</idno>
                  <idno type="idhal" notation="numeric">10815</idno>
                  <idno type="halauthorid" notation="string">3552-10815</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0977-2926</idno>
                  <idno type="IDREF">https://www.idref.fr/154913634</idno>
                  <affiliation ref="#struct-1625"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Iris</forename>
                    <surname>Eshkol</surname>
                  </persName>
                  <email type="md5">7924056b460473adb79b923b51531c99</email>
                  <email type="domain">parisnanterre.fr</email>
                  <idno type="idhal" notation="string">iris-eshkol-taravella</idno>
                  <idno type="idhal" notation="numeric">18520</idno>
                  <idno type="halauthorid" notation="string">194454-18520</idno>
                  <idno type="IDREF">https://www.idref.fr/074195158</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0814-3623</idno>
                  <affiliation ref="#struct-16494"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Samer</forename>
                    <surname>Taalab</surname>
                  </persName>
                  <idno type="halauthorid">445274-0</idno>
                  <affiliation ref="#struct-1625"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jean-Philippe</forename>
                    <surname>Prost</surname>
                  </persName>
                  <email type="md5">6bfbf10058b33ad912f15f9f9d513006</email>
                  <email type="domain">univ-amu.fr</email>
                  <idno type="idhal" notation="string">jean-philippe-prost</idno>
                  <idno type="idhal" notation="numeric">13248</idno>
                  <idno type="halauthorid" notation="string">18272-13248</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2804-9191</idno>
                  <idno type="IDREF">https://www.idref.fr/146636635</idno>
                  <affiliation ref="#struct-1625"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">148180</idno>
                <idno type="issn">1870-4069</idno>
                <title level="j">Research in Computing Science</title>
                <title level="m">Special Issue: Natural Language Processing and its Applications</title>
                <meeting>
                  <title>11th international Conference on Intelligent Text Processing and Computational Linguistics</title>
                  <date type="start">2010-03-21</date>
                  <date type="end">2010-03-27</date>
                  <settlement>Iasi</settlement>
                  <country key="RO">Romania</country>
                </meeting>
                <editor>Alexander Gelbukh</editor>
                <imprint>
                  <publisher>National Polytechnic Institute</publisher>
                  <biblScope unit="volume">46</biblScope>
                  <biblScope unit="pp">79--90</biblScope>
                  <date type="datePub">2010-03</date>
                </imprint>
              </monogr>
              <ref type="publisher">http://www.cicling.org/2010/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <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="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>The ESLO (Enquête sociolinguistique d'Orléans, i.e. Sociolinguistic Survey of Orléans) campaign gathered a large oral corpus, which was later transcribed into a text format. The purpose of this work is to assign morpho-syntactic labels to each unit of this corpus. To this end, we first studied the specificities of the labels required for oral data, and their various possible levels of description. This led to a new original hierarchical structure of labels. Then, since our new set of labels was different from any of those of existing taggers, which are usually not fit for oral data, we have built a new labelling tool using a Machine Learning approach. As a starting point, we used data labelled by Cordial and corrected by hand. We used CRF (Conditional Random Fields), to try to take the best possible advantage of the linguistic knowledge used to define the set of labels. We measure accuracy between 85 and 90, depending on the parameters.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1625" status="OLD">
          <idno type="IdRef">075434695</idno>
          <idno type="RNSR">200615274F</idno>
          <orgName>Laboratoire d'Informatique Fondamentale d'Orléans</orgName>
          <orgName type="acronym">LIFO</orgName>
          <date type="start">1987-01-01</date>
          <date type="end">2013-12-31</date>
          <desc>
            <address>
              <addrLine>Batiment IIIA 6 Rue Léonard de Vinci - BP 6759 45067 ORLEANS CEDEX 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-orleans.fr/lifo/</ref>
          </desc>
          <listRelation>
            <relation name="EA4022" active="#struct-300297" type="direct"/>
            <relation name="EA4022" active="#struct-300379" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-16494" status="OLD">
          <orgName>Centre Orléanais de Recherches en Anthropologie et Linguistique</orgName>
          <orgName type="acronym">CORAL</orgName>
          <desc>
            <address>
              <addrLine>Faculté de Lettres, Langues et Sciences Humaines - 10, rue de Tours - BP 46527 - 45065 Orléans Cedex 2</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-300297" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300297" status="VALID">
          <idno type="IdRef">026402971</idno>
          <idno type="ISNI">0000 0001 2158 1666</idno>
          <idno type="ROR">https://ror.org/014zrew76</idno>
          <orgName>Université d'Orléans</orgName>
          <orgName type="acronym">UO</orgName>
          <desc>
            <address>
              <addrLine>Château de la Source - Avenue du Parc Floral - BP 6749 - 45067 Orléans cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-orleans.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300379" status="VALID">
          <orgName>Ecole Nationale Supérieure d'Ingénieurs de Bourges</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-4075" status="VALID">
          <idno type="anr">ANR-07-MDCO-0003</idno>
          <idno type="program">Masse de données Connaissances Ambiantes</idno>
          <orgName>CROTAL</orgName>
          <desc>Conditional Random fields pour le TAL</desc>
          <date type="start">2007</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>