<?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-04854981</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="2026-05-22T16:35:28+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">KGConv, a Conversational Corpus grounded in Wikidata</title>
            <author role="aut">
              <persName>
                <forename type="first">Quentin</forename>
                <surname>Brabant</surname>
              </persName>
              <idno type="halauthorid">28232-0</idno>
              <affiliation ref="#struct-1087506"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Lina</forename>
                <forename type="middle">M</forename>
                <surname>Rojas-Barahona</surname>
              </persName>
              <email type="md5">6250c7219f124d705c6c7e81facfced8</email>
              <email type="domain">orange.com</email>
              <idno type="idhal" notation="string">lina-rojas</idno>
              <idno type="idhal" notation="numeric">1123589</idno>
              <idno type="halauthorid" notation="string">2854497-1123589</idno>
              <idno type="ARXIV">https://arxiv.org/a/rojasbarahona_l_1</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=n42dh0cAAAAJ</idno>
              <idno type="ORCID">https://orcid.org/0009-0009-8439-4695</idno>
              <affiliation ref="#struct-1087506"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gwénolé</forename>
                <surname>Lecorvé</surname>
              </persName>
              <email type="md5">e9e3c2e393d6f91299d5f272789d1964</email>
              <email type="domain">orange.com</email>
              <idno type="idhal" notation="string">gwenole-lecorve</idno>
              <idno type="idhal" notation="numeric">20677</idno>
              <idno type="halauthorid" notation="string">21402-20677</idno>
              <idno type="IDREF">https://www.idref.fr/150245254</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4271-2087</idno>
              <idno type="ARXIV">https://arxiv.org/a/lecorve_g_1</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=EGC_mugAAAAJ</idno>
              <affiliation ref="#struct-1087506"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Claire</forename>
                <surname>Gardent</surname>
              </persName>
              <email type="md5">2011a70cc805f691b71fc804cd7fac0e</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">claire-gardent</idno>
              <idno type="idhal" notation="numeric">3949</idno>
              <idno type="halauthorid" notation="string">16753-3949</idno>
              <idno type="IDREF">https://www.idref.fr/034104593</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3805-6662</idno>
              <affiliation ref="#struct-178243"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Claire</forename>
                <surname>Gardent</surname>
              </persName>
              <email type="md5">2011a70cc805f691b71fc804cd7fac0e</email>
              <email type="domain">loria.fr</email>
            </editor>
            <funder ref="#projeurop-714098"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-12-24 08:49:31</date>
              <date type="whenModified">2025-11-04 12:04:56</date>
              <date type="whenReleased">2025-01-06 11:55:30</date>
              <date type="whenProduced">2024-05-20</date>
              <date type="whenEndEmbargoed">2024-12-24</date>
              <ref type="file" target="https://cnrs.hal.science/hal-04854981v1/document">
                <date notBefore="2024-12-24"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://cnrs.hal.science/hal-04854981v1/file/2024.lrec-main.850.pdf" id="file-4854981-4231547">
                <date notBefore="2024-12-24"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="103135">
                <persName>
                  <forename>Claire</forename>
                  <surname>Gardent</surname>
                </persName>
                <email type="md5">2011a70cc805f691b71fc804cd7fac0e</email>
                <email type="domain">loria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04854981</idno>
            <idno type="halUri">https://cnrs.hal.science/hal-04854981</idno>
            <idno type="halBibtex">brabant:hal-04854981</idno>
            <idno type="halRefHtml">&lt;i&gt;The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)&lt;/i&gt;, LREC, May 2024, Turin, Italy</idno>
            <idno type="halRef">The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), LREC, May 2024, Turin, Italy</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-nc/4.0/">CC BY-NC 4.0 - Attribution - Non-commercial use<ref corresp="#file-4854981-4231547"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="OPENAIRE">OpenAIRE</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
            <idno type="stamp" n="LORIA">Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
            <idno type="stamp" n="LORIA-NLPKD" corresp="LORIA">Department of Natural Language Processing &amp; Knowledge Discovery</idno>
            <idno type="stamp" n="AM2I-UL">Pôle scientifique Automatique, Mathématiques, Informatique et leurs Intéractions de l'Université de Lorraine</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">KGConv, a Conversational Corpus grounded in Wikidata</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Quentin</forename>
                    <surname>Brabant</surname>
                  </persName>
                  <idno type="halauthorid">28232-0</idno>
                  <affiliation ref="#struct-1087506"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Lina</forename>
                    <forename type="middle">M</forename>
                    <surname>Rojas-Barahona</surname>
                  </persName>
                  <email type="md5">6250c7219f124d705c6c7e81facfced8</email>
                  <email type="domain">orange.com</email>
                  <idno type="idhal" notation="string">lina-rojas</idno>
                  <idno type="idhal" notation="numeric">1123589</idno>
                  <idno type="halauthorid" notation="string">2854497-1123589</idno>
                  <idno type="ARXIV">https://arxiv.org/a/rojasbarahona_l_1</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=n42dh0cAAAAJ</idno>
                  <idno type="ORCID">https://orcid.org/0009-0009-8439-4695</idno>
                  <affiliation ref="#struct-1087506"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gwénolé</forename>
                    <surname>Lecorvé</surname>
                  </persName>
                  <email type="md5">e9e3c2e393d6f91299d5f272789d1964</email>
                  <email type="domain">orange.com</email>
                  <idno type="idhal" notation="string">gwenole-lecorve</idno>
                  <idno type="idhal" notation="numeric">20677</idno>
                  <idno type="halauthorid" notation="string">21402-20677</idno>
                  <idno type="IDREF">https://www.idref.fr/150245254</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4271-2087</idno>
                  <idno type="ARXIV">https://arxiv.org/a/lecorve_g_1</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=EGC_mugAAAAJ</idno>
                  <affiliation ref="#struct-1087506"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Claire</forename>
                    <surname>Gardent</surname>
                  </persName>
                  <email type="md5">2011a70cc805f691b71fc804cd7fac0e</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">claire-gardent</idno>
                  <idno type="idhal" notation="numeric">3949</idno>
                  <idno type="halauthorid" notation="string">16753-3949</idno>
                  <idno type="IDREF">https://www.idref.fr/034104593</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3805-6662</idno>
                  <affiliation ref="#struct-178243"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
                <meeting>
                  <title>The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
                  <date type="start">2024-05-20</date>
                  <date type="end">2024-05-24</date>
                  <settlement>Turin</settlement>
                  <country key="IT">Italy</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>LREC</name>
                </respStmt>
                <imprint>
                  <date type="datePub">2024-05-20</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Dialogue</term>
                <term xml:lang="en">Knowledge Base</term>
                <term xml:lang="en">Conversational Question Generation</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</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>We present KGConv, a large corpus of 71k English conversations where each question-answer pair is grounded in a Wikidata fact. The conversations were generated automatically: in particular, questions were created using a collection of 10,355 templates; subsequently, the naturalness of conversations was improved by inserting ellipses and coreference into questions, via both handcrafted rules and a generative rewriting model. The dataset thus provides several variants of each question (12 on average), organized into 3 levels of conversationality. We provide baselines for the task of Knowledge-Based Conversational Question Generation. KGConv can further be used for other generation and analysis tasks such as single-turn question generation from Wikidata triples, question rewriting, question answering from conversation or from knowledge graphs and quiz generation.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-1087506" status="VALID">
          <orgName>Orange S.A.</orgName>
          <desc>
            <address>
              <addrLine>111, quai du Président Roosevelt92449 ISSY LES MOULINEAUX</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-178243" status="VALID">
          <orgName>Natural Language Processing : representations, inference and semantics</orgName>
          <orgName type="acronym">SYNALP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/la-recherche-en/equipes/synalp</ref>
          </desc>
          <listRelation>
            <relation active="#struct-423086" type="direct"/>
            <relation active="#struct-206040" type="indirect"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="department" xml:id="struct-423086" status="VALID">
          <orgName>Department of Natural Language Processing &amp; Knowledge Discovery</orgName>
          <orgName type="acronym">LORIA - NLPKD</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/en/research/departments/natural-language-processing-and-knowledge-discovery/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-206040" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-206040" status="VALID">
          <idno type="IdRef">067077927</idno>
          <idno type="ISNI">0000000121795429</idno>
          <idno type="RNSR">198912571S</idno>
          <idno type="IdUnivLorraine">[UL]RSI--</idno>
          <idno type="ROR">https://ror.org/02vnf0c38</idno>
          <orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
          <orgName type="acronym">LORIA</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
            <relation name="UMR7503" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-413289" status="VALID">
          <idno type="IdRef">157040569</idno>
          <idno type="IdUnivLorraine">[UL]100--</idno>
          <idno type="ROR">https://ror.org/04vfs2w97</idno>
          <orgName>Université de Lorraine</orgName>
          <orgName type="acronym">UL</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lorraine.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="europeanProject" xml:id="projeurop-714098" status="VALID">
          <idno type="number">860621</idno>
          <idno type="program">H2020-MSCA-ITN-2019</idno>
          <idno type="call">H2020-MSCA-ITN-2019</idno>
          <orgName>NL4XAI</orgName>
          <desc>Interactive Natural Language Technology for  Explainable Artificial Intelligence</desc>
          <date type="start">2019-10-01</date>
          <date type="end">2024-09-30</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>