<?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-03089957</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="2026-05-22T16:48:43+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Voting Classifier vs Deep learning method in Arabic Dialect Identification</title>
            <author role="aut">
              <persName>
                <forename type="first">Dhaou</forename>
                <surname>Ghoul</surname>
              </persName>
              <email type="md5">1bcf321495159b9172efa6c1af23da31</email>
              <email type="domain">sorbonne-universite.fr</email>
              <idno type="idhal" notation="numeric">1072388</idno>
              <idno type="halauthorid" notation="string">590332-1072388</idno>
              <affiliation ref="#struct-542233"/>
              <affiliation ref="#struct-551720"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gaël</forename>
                <surname>Lejeune</surname>
              </persName>
              <email type="md5">740064454f6f51a7f88b35f2e820639c</email>
              <email type="domain">paris-sorbonne.fr</email>
              <idno type="idhal" notation="string">gael-lejeune</idno>
              <idno type="idhal" notation="numeric">734695</idno>
              <idno type="halauthorid" notation="string">37811-734695</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4795-2362</idno>
              <idno type="IDREF">https://www.idref.fr/182283054</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/DDF-6252-2022</idno>
              <idno type="VIAF">https://viaf.org/viaf/313310259</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/DDF-6252-2022</idno>
              <affiliation ref="#struct-186676"/>
              <affiliation ref="#struct-551720"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Gaël</forename>
                <surname>Lejeune</surname>
              </persName>
              <email type="md5">740064454f6f51a7f88b35f2e820639c</email>
              <email type="domain">paris-sorbonne.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-12-29 07:26:47</date>
              <date type="whenModified">2024-10-29 13:15:43</date>
              <date type="whenReleased">2021-01-13 10:21:50</date>
              <date type="whenProduced">2020-12-08</date>
              <date type="whenEndEmbargoed">2020-12-29</date>
              <ref type="file" target="https://hal.science/hal-03089957v1/document">
                <date notBefore="2020-12-29"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03089957v1/file/coling2020.pdf" id="file-3089957-2703725">
                <date notBefore="2020-12-29"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="402810">
                <persName>
                  <forename>Gaël</forename>
                  <surname>Lejeune</surname>
                </persName>
                <email type="md5">740064454f6f51a7f88b35f2e820639c</email>
                <email type="domain">paris-sorbonne.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03089957</idno>
            <idno type="halUri">https://hal.science/hal-03089957</idno>
            <idno type="halBibtex">ghoul:hal-03089957</idno>
            <idno type="halRefHtml">&lt;i&gt;: Proceedings of the Fifth Arabic Natural Language Processing Workshop, COLING 2020&lt;/i&gt;, Dec 2020, Barcelone, Spain</idno>
            <idno type="halRef">: Proceedings of the Fifth Arabic Natural Language Processing Workshop, COLING 2020, Dec 2020, Barcelone, Spain</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3089957-2703725"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SORBONNE-UNIV" corresp="SORBONNE-UNIVERSITE">Sorbonne Université 01/01/2018</idno>
            <idno type="stamp" n="STIH" corresp="SORBONNE-UNIVERSITE">Sens, Texte, Informatique, Histoire</idno>
            <idno type="stamp" n="SU-LETTRES" corresp="SORBONNE-UNIVERSITE">Faculté des Lettres de Sorbonne Université</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="SUPRA_SHS3467">SUPRA SHS3467</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">Voting Classifier vs Deep learning method in Arabic Dialect Identification</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Dhaou</forename>
                    <surname>Ghoul</surname>
                  </persName>
                  <email type="md5">1bcf321495159b9172efa6c1af23da31</email>
                  <email type="domain">sorbonne-universite.fr</email>
                  <idno type="idhal" notation="numeric">1072388</idno>
                  <idno type="halauthorid" notation="string">590332-1072388</idno>
                  <affiliation ref="#struct-542233"/>
                  <affiliation ref="#struct-551720"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gaël</forename>
                    <surname>Lejeune</surname>
                  </persName>
                  <email type="md5">740064454f6f51a7f88b35f2e820639c</email>
                  <email type="domain">paris-sorbonne.fr</email>
                  <idno type="idhal" notation="string">gael-lejeune</idno>
                  <idno type="idhal" notation="numeric">734695</idno>
                  <idno type="halauthorid" notation="string">37811-734695</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4795-2362</idno>
                  <idno type="IDREF">https://www.idref.fr/182283054</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/DDF-6252-2022</idno>
                  <idno type="VIAF">https://viaf.org/viaf/313310259</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/DDF-6252-2022</idno>
                  <affiliation ref="#struct-186676"/>
                  <affiliation ref="#struct-551720"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of the Fifth Arabic Natural Language Processing Workshop, COLING 2020</title>
                <meeting>
                  <title>: Proceedings of the Fifth Arabic Natural Language Processing Workshop, COLING 2020</title>
                  <date type="start">2020-12-08</date>
                  <settlement>Barcelone</settlement>
                  <country key="ES">Spain</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <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>In this paper, we present three methods developed by the SORBONNE Team for the NADI shared task on Arabic Dialect Identification for tweets. The first and the second method use respectively a machine learning model based on a Voting Classifier with words and character level features and a deep learning model at the word level. The third method uses only character-level features. We explored different text representation such as TF-IDF (first model) and word embeddings (second model). The Voting Classifier was the most powerful prediction model, achieving the best macro-average F1 score of 18.8% and an accuracy of 36.54% on the official test. Our model ranked 9 on the challenge and in conclusion we propose some ideas to improve its results.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-542233" status="VALID">
          <idno type="IdRef">149171617</idno>
          <idno type="RNSR">201019031X</idno>
          <orgName>Sens, Texte, Informatique, Histoire</orgName>
          <orgName type="acronym">STIH</orgName>
          <desc>
            <address>
              <addrLine>1 rue Victor Cousin 75230 Paris cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.stih.paris-sorbonne.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA4509" active="#struct-413221" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-551720" status="VALID">
          <orgName>Équipe Linguistique computationnelle</orgName>
          <orgName type="acronym">STIH-LC</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-542233" type="direct"/>
            <relation name="EA4509" active="#struct-413221" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-186676" status="OLD">
          <idno type="IdRef">149171617</idno>
          <idno type="RNSR">201019031X</idno>
          <idno type="ROR">https://ror.org/02q5emw59</idno>
          <orgName>Sens, Texte, Informatique, Histoire</orgName>
          <orgName type="acronym">STIH</orgName>
          <desc>
            <address>
              <addrLine>1 rue Victor Cousin 75230 Paris cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.stih.paris-sorbonne.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA4509" active="#struct-123821" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-413221" status="VALID">
          <idno type="IdRef">221333754</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Sorbonne Université</orgName>
          <orgName type="acronym">SU</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>21 rue de l’École de médecine - 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-universite.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-123821" status="OLD">
          <idno type="IdRef">026403633</idno>
          <idno type="ISNI">000000012165487X</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Université Paris-Sorbonne</orgName>
          <orgName type="acronym">UP4</orgName>
          <date type="start">1971-01-01</date>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>1 rue Victor Cousin - 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.paris-sorbonne.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>