<?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-03832361</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="2026-04-29T04:50:22+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Do children texts hold the key to commonsense knowledge?</title>
            <author role="aut">
              <persName>
                <forename type="first">Julien</forename>
                <surname>Romero</surname>
              </persName>
              <email type="md5">3eedd087103e32b504a9c207d253f27d</email>
              <email type="domain">telecom-sudparis.eu</email>
              <idno type="idhal" notation="string">julienromero</idno>
              <idno type="idhal" notation="numeric">751522</idno>
              <idno type="halauthorid" notation="string">51549-751522</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7382-9077</idno>
              <affiliation ref="#struct-563936"/>
              <affiliation ref="#struct-352124"/>
              <affiliation ref="#struct-5170"/>
              <affiliation ref="#struct-442703"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Simon</forename>
                <surname>Razniewski</surname>
              </persName>
              <idno type="halauthorid">1136656-0</idno>
              <affiliation ref="#struct-54489"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Julien</forename>
                <surname>Romero</surname>
              </persName>
              <email type="md5">3eedd087103e32b504a9c207d253f27d</email>
              <email type="domain">telecom-sudparis.eu</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-10-27 16:01:29</date>
              <date type="whenModified">2026-02-18 14:06:01</date>
              <date type="whenReleased">2022-11-02 10:50:17</date>
              <date type="whenProduced">2022-12-07</date>
              <date type="whenEndEmbargoed">2022-10-27</date>
              <ref type="file" target="https://hal.science/hal-03832361v1/document">
                <date notBefore="2022-10-27"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03832361v1/file/kid_books-1.pdf" id="file-3832361-3351951">
                <date notBefore="2022-10-27"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="701743">
                <persName>
                  <forename>Julien</forename>
                  <surname>Romero</surname>
                </persName>
                <email type="md5">3eedd087103e32b504a9c207d253f27d</email>
                <email type="domain">telecom-sudparis.eu</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03832361</idno>
            <idno type="halUri">https://hal.science/hal-03832361</idno>
            <idno type="halBibtex">romero:hal-03832361</idno>
            <idno type="halRefHtml">&lt;i&gt;EMNLP 2022: The 2022 Conference on Empirical Methods in Natural Language Processing&lt;/i&gt;, Dec 2022, Abu Dhabi, France</idno>
            <idno type="halRef">EMNLP 2022: The 2022 Conference on Empirical Methods in Natural Language Processing, Dec 2022, Abu Dhabi, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3832361-3351951"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="TELECOM-SUDPARIS" corresp="INSTITUT-MINES-TELECOM">Télécom SudParis</idno>
            <idno type="stamp" n="IP_PARIS">Institut Polytechnique de Paris</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="INSTITUT-MINES-TELECOM">Institut Mines Telecom</idno>
            <idno type="stamp" n="IP-PARIS-DEPARTEMENT-MATHEMATIQUES">Département de Mathèmatiques</idno>
            <idno type="stamp" n="IP-PARIS-MATHEMATIQUES">IP Paris Département de Mathématiques</idno>
            <idno type="stamp" n="IP-PARIS-INFORMATION-COMMUNICATION-ELECTRONIQUE">IP Paris Département d'Information, de Communication et d'Électronique</idno>
            <idno type="stamp" n="IP-PARIS-INFORMATIQUE-DONNEES-ET-IA">IP Paris Département d'Informatique, de Données et d'IA</idno>
            <idno type="stamp" n="SAMOVAR">Services répartis, Architectures, Modélisation, Validation, Administration des Réseaux</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">Do children texts hold the key to commonsense knowledge?</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Julien</forename>
                    <surname>Romero</surname>
                  </persName>
                  <email type="md5">3eedd087103e32b504a9c207d253f27d</email>
                  <email type="domain">telecom-sudparis.eu</email>
                  <idno type="idhal" notation="string">julienromero</idno>
                  <idno type="idhal" notation="numeric">751522</idno>
                  <idno type="halauthorid" notation="string">51549-751522</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7382-9077</idno>
                  <affiliation ref="#struct-563936"/>
                  <affiliation ref="#struct-352124"/>
                  <affiliation ref="#struct-5170"/>
                  <affiliation ref="#struct-442703"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Simon</forename>
                    <surname>Razniewski</surname>
                  </persName>
                  <idno type="halauthorid">1136656-0</idno>
                  <affiliation ref="#struct-54489"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">The 2022 Conference on Empirical Methods in Natural Language Processing</title>
                <meeting>
                  <title>EMNLP 2022: The 2022 Conference on Empirical Methods in Natural Language Processing</title>
                  <date type="start">2022-12-07</date>
                  <settlement>Abu Dhabi</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">AI</term>
                <term xml:lang="en">Artifial intelligence</term>
                <term xml:lang="en">Commonsense Knowledge</term>
                <term xml:lang="en">CHILDREN</term>
                <term xml:lang="en">LANGUAGES</term>
                <term xml:lang="en">LANGUAGE PROCESSING</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</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>Compiling comprehensive repositories of commonsense knowledge is a long-standing problem in AI. Many concerns revolve around the issue of reporting bias, i.e., that frequency in text sources is not a good proxy for relevance or truth. This paper explores whether children's texts hold the key to commonsense knowledge compilation, based on the hypothesis that such content makes fewer assumptions on the reader's knowledge, and therefore spells out commonsense more explicitly. An analysis with several corpora shows that children's texts indeed contain much more, and more typical commonsense assertions. Moreover, experiments show that this advantage can be leveraged in popular language-model-based commonsense knowledge extraction settings, where task-unspecific fine-tuning on small amounts of children texts (childBERT) already yields significant improvements. This provides a refreshing perspective different from the common trend of deriving progress from ever larger models and corpora.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="regroupinstitution" xml:id="struct-563936" status="VALID">
          <idno type="IdRef">238327159</idno>
          <idno type="ISNI">0000000502717600</idno>
          <idno type="ROR">https://ror.org/042tfbd02</idno>
          <idno type="Wikidata">Q48759778</idno>
          <orgName>Institut Polytechnique de Paris</orgName>
          <orgName type="acronym">IP Paris</orgName>
          <date type="start">2019-06-02</date>
          <desc>
            <address>
              <addrLine>Route de Saclay, 91120 Palaiseau Cedex, France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ip-paris.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-352124" status="VALID">
          <idno type="IdRef">162347510</idno>
          <idno type="ISNI">0000000406406351</idno>
          <idno type="ROR">https://ror.org/05xvk4r52</idno>
          <idno type="Wikidata">Q43305</idno>
          <orgName>Télécom SudParis</orgName>
          <orgName type="acronym">TSP</orgName>
          <desc>
            <address>
              <addrLine>9 rue Charles Fourier -91011 Evry Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.telecom-sudparis.eu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
            <relation name="563936" active="#struct-563936" type="direct"/>
          </listRelation>
        </org>
        <org type="department" xml:id="struct-5170" status="VALID">
          <orgName>Département Informatique</orgName>
          <orgName type="acronym">TSP - INF</orgName>
          <desc>
            <address>
              <addrLine>Télécom SudParis - 9 rue Charles Fourier. 91011 Évry Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www-inf.int-evry.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-352124" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
            <relation name="563936" active="#struct-563936" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-442703" status="VALID">
          <orgName>Architecture, Cloud continuum, formal Models, artificial intElligence and Services in distributed computing</orgName>
          <orgName type="acronym">ACMES-SAMOVAR</orgName>
          <desc>
            <address>
              <addrLine>TELECOM Sudparis 9 rue Charles Fourier 91011 EVRY</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://samovar.telecom-sudparis.eu</ref>
          </desc>
          <listRelation>
            <relation active="#struct-638" type="direct"/>
            <relation active="#struct-352124" type="indirect"/>
            <relation active="#struct-302102" type="indirect"/>
            <relation name="563936" active="#struct-563936" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-54489" status="VALID">
          <orgName>Max-Planck-Institut für Informatik</orgName>
          <orgName type="acronym">MPII</orgName>
          <desc>
            <address>
              <addrLine>Campus E-1 4, 66123 Saarbrücken, Germany</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">http://www.mpi-inf.mpg.de/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-5247" 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>
        <org type="laboratory" xml:id="struct-638" status="VALID">
          <idno type="IdRef">281286515</idno>
          <idno type="ISNI">0000000403830480</idno>
          <idno type="RNSR">200319330C</idno>
          <orgName>Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux</orgName>
          <orgName type="acronym">SAMOVAR</orgName>
          <desc>
            <address>
              <addrLine>Télécom Sudparis, 9 rue Charles Fourier -91011 Evry cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://samovar.telecom-sudparis.eu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-352124" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
            <relation name="563936" active="#struct-563936" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-5247" status="VALID">
          <orgName>Max-Planck-Gesellschaft</orgName>
          <desc>
            <address>
              <addrLine>Jägerstrasse, 10-11, D-10117 Berlin</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.mpg.de/en</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>