<?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-01537896</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="2026-05-20T01:39:40+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A comparative study of target-based and entity-based opinion extraction</title>
            <author role="aut">
              <persName>
                <forename type="first">Joseph</forename>
                <surname>Lark</surname>
              </persName>
              <idno type="idhal" notation="numeric">1010265</idno>
              <idno type="halauthorid" notation="string">907176-1010265</idno>
              <affiliation ref="#struct-473973"/>
              <affiliation ref="#struct-418308"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Emmanuel</forename>
                <surname>Morin</surname>
              </persName>
              <email type="md5">c0fdbead319f36903512d4d180789e48</email>
              <email type="domain">univ-nantes.fr</email>
              <idno type="idhal" notation="string">emmanuel-morin</idno>
              <idno type="idhal" notation="numeric">3632</idno>
              <idno type="halauthorid" notation="string">20798-3632</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-8208-7039</idno>
              <idno type="IDREF">https://www.idref.fr/14379373X</idno>
              <affiliation ref="#struct-473973"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sebastián</forename>
                <forename type="middle">Peña</forename>
                <surname>Saldarriaga</surname>
              </persName>
              <email type="md5">9d7f089492c2e25f7d35e53db7c18eb4</email>
              <email type="domain">dictanova.com</email>
              <idno type="idhal" notation="numeric">965687</idno>
              <idno type="halauthorid" notation="string">1180668-965687</idno>
              <affiliation ref="#struct-418308"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Joseph</forename>
                <surname>Lark</surname>
              </persName>
              <email type="md5">8a475e030420d7fad89ccc8d24cd901c</email>
              <email type="domain">monemail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2017-06-13 10:32:15</date>
              <date type="whenWritten">2017-02</date>
              <date type="whenModified">2026-02-07 05:13:48</date>
              <date type="whenReleased">2017-06-16 11:38:03</date>
              <date type="whenProduced">2017-04-17</date>
              <date type="whenEndEmbargoed">2017-06-13</date>
              <ref type="file" target="https://hal.science/hal-01537896v1/document">
                <date notBefore="2017-06-13"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01537896v1/file/paper_42.pdf" id="file-1537896-1597487">
                <date notBefore="2017-06-13"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="313253">
                <persName>
                  <forename>Joseph</forename>
                  <surname>Lark</surname>
                </persName>
                <email type="md5">8a475e030420d7fad89ccc8d24cd901c</email>
                <email type="domain">monemail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01537896</idno>
            <idno type="halUri">https://hal.science/hal-01537896</idno>
            <idno type="halBibtex">lark:hal-01537896</idno>
            <idno type="halRefHtml">&lt;i&gt;18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)&lt;/i&gt;, Apr 2017, Budapest, Hungary. &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-319-77116-8_16"&gt;&amp;#x27E8;10.1007/978-3-319-77116-8_16&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing), Apr 2017, Budapest, Hungary. &amp;#x27E8;10.1007/978-3-319-77116-8_16&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1537896-1597487"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-NANTES">Université de Nantes</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="EC-NANTES">Ecole Centrale de Nantes</idno>
            <idno type="stamp" n="UNAM">l'unam - université nantes angers le mans</idno>
            <idno type="stamp" n="LS2N">Laboratoire des Sciences du Numérique de Nantes</idno>
            <idno type="stamp" n="LS2N-TALN" corresp="LS2N">LS2N - équipe TALN ( Traitement Automatique du Langage Naturel )</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="NANTES-UNIVERSITE">Nantes Université</idno>
            <idno type="stamp" n="UNIV-NANTES-AV2022">Université de Nantes</idno>
            <idno type="stamp" n="NU-CENTRALE">École Centrale de Nantes</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 comparative study of target-based and entity-based opinion extraction</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Joseph</forename>
                    <surname>Lark</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1010265</idno>
                  <idno type="halauthorid" notation="string">907176-1010265</idno>
                  <affiliation ref="#struct-473973"/>
                  <affiliation ref="#struct-418308"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Emmanuel</forename>
                    <surname>Morin</surname>
                  </persName>
                  <email type="md5">c0fdbead319f36903512d4d180789e48</email>
                  <email type="domain">univ-nantes.fr</email>
                  <idno type="idhal" notation="string">emmanuel-morin</idno>
                  <idno type="idhal" notation="numeric">3632</idno>
                  <idno type="halauthorid" notation="string">20798-3632</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-8208-7039</idno>
                  <idno type="IDREF">https://www.idref.fr/14379373X</idno>
                  <affiliation ref="#struct-473973"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sebastián</forename>
                    <forename type="middle">Peña</forename>
                    <surname>Saldarriaga</surname>
                  </persName>
                  <email type="md5">9d7f089492c2e25f7d35e53db7c18eb4</email>
                  <email type="domain">dictanova.com</email>
                  <idno type="idhal" notation="numeric">965687</idno>
                  <idno type="halauthorid" notation="string">1180668-965687</idno>
                  <affiliation ref="#struct-418308"/>
                </author>
              </analytic>
              <monogr>
                <idno type="localRef">ACTI</idno>
                <title level="m">Proceedings of CICLing 2017</title>
                <meeting>
                  <title>18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)</title>
                  <date type="start">2017-04-17</date>
                  <date type="end">2017-04-23</date>
                  <settlement>Budapest</settlement>
                  <country key="HU">Hungary</country>
                </meeting>
                <imprint>
                  <date type="datePub">2017-04</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-319-77116-8_16</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">aspect-based sentiment analysis</term>
                <term xml:lang="en">annotation</term>
                <term xml:lang="en">opinion mining</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ir">Computer Science [cs]/Information Retrieval [cs.IR]</classCode>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</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>Opinion target extraction is a crucial task of opinion mining, aiming to extract occurrences of the different entities of a corpus that are subjects of an opinion. In order to produce a readable and comprehen-sible opinion summary, these occurrences are aggregated under higher order labels, or entities, in a second task. In this paper we argue that combining the two tasks, i.e. extracting opinion targets using entities as labels instead of binary labels, yields better results for opinion extraction. We compare the binary and the multi-class approaches on available datasets in English and French, and conduct several investigation experiments to explain the promising results. Our experiments show that an entity-based labelling not only improves opinion extraction in a single domain setting, but also let us combine training data from different domains to improve the extraction, a result that has never been observed on target-based training data.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-473973" status="OLD">
          <idno type="IdRef">203637585</idno>
          <idno type="RNSR">201722241F</idno>
          <idno type="ROR">https://ror.org/02snf8m58</idno>
          <orgName>Laboratoire des Sciences du Numérique de Nantes</orgName>
          <orgName type="acronym">LS2N</orgName>
          <date type="start">2017-01-01</date>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>Université de Nantes – faculté des Sciences et Techniques (FST)2 Chemin de la HoussinièreBP 92208, 44322 Nantes Cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ls2n.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-97058" type="direct"/>
            <relation active="#struct-93263" type="indirect"/>
            <relation active="#struct-111023" type="direct"/>
            <relation name="UMR6004" active="#struct-441569" type="direct"/>
            <relation active="#struct-481355" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-418308" status="INCOMING">
          <orgName>Dictanova</orgName>
          <desc>
            <address>
              <addrLine>2 Chemin de la Houssinière, 44300 Nantes</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.dictanova.com/</ref>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-97058" status="OLD">
          <orgName>Université de Nantes - UFR des Sciences et des Techniques</orgName>
          <orgName type="acronym">UN UFR ST</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>2, rue de la Houssinière - BP 92208 - 44322 Nantes cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sciences-techniques.univ-nantes.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-93263" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-93263" status="OLD">
          <idno type="IdRef">026403447</idno>
          <idno type="ROR">https://ror.org/03gnr7b55</idno>
          <orgName>Université de Nantes</orgName>
          <orgName type="acronym">UN</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>1, quai de Tourville - BP 13522 - 44035 Nantes cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-nantes.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-111023" status="OLD">
          <idno type="IdRef">03063525X</idno>
          <idno type="ISNI">0000000122039289</idno>
          <idno type="ROR">https://ror.org/03nh7d505</idno>
          <orgName>École Centrale de Nantes</orgName>
          <orgName type="acronym">ECN</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>1 rue de la Noë - BP 92101 - 44321 Nantes cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ec-nantes.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-481355" status="VALID">
          <idno type="IdRef">202743233</idno>
          <idno type="ROR">https://ror.org/030hj3061</idno>
          <orgName>IMT Atlantique</orgName>
          <orgName type="acronym">IMT Atlantique</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Brest : Technopôle Brest-Iroise CS 8381829238 BREST Cedex 3 -Campus Nantes : 4, rue Alfred Kastler- La chantrerie 44300 NANTES -Campus Rennes :  2 Rue de la Châtaigneraie, 35510 CESSON SEVIGNE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt-atlantique.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-302102" status="VALID">
          <idno type="IdRef">192427156</idno>
          <idno type="ISNI">000000012202567X</idno>
          <idno type="ROR">https://ror.org/025vp2923</idno>
          <idno type="Wikidata">Q27962533</idno>
          <orgName>Institut Mines-Télécom [Paris]</orgName>
          <orgName type="acronym">IMT</orgName>
          <date type="start">2012-03-01</date>
          <desc>
            <address>
              <addrLine>19 Place Marguerite Perey, 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>