<?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-02560196</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="2026-05-14T19:27:22+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Human-in-the-Loop Schema Inference for Massive JSON Datasets</title>
            <author role="aut">
              <persName>
                <forename type="first">Mohamed-Amine</forename>
                <surname>Baazizi</surname>
              </persName>
              <email type="md5">a49d58f1bfaafd3ba167627d29382132</email>
              <email type="domain">lip6.fr</email>
              <idno type="idhal" notation="string">mohamed-amine-baazizi</idno>
              <idno type="idhal" notation="numeric">13062</idno>
              <idno type="halauthorid" notation="string">26388-13062</idno>
              <idno type="IDREF">https://www.idref.fr/162548923</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2728-5838</idno>
              <affiliation ref="#struct-541715"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Clément</forename>
                <surname>Berti</surname>
              </persName>
              <email type="md5">2e1896bbae36c028b62309d34713c412</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">1068994</idno>
              <idno type="halauthorid" notation="string">1836209-1068994</idno>
              <affiliation ref="#struct-413221"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Dario</forename>
                <surname>Colazzo</surname>
              </persName>
              <email type="md5">656cc7989e90a4924f1c484d5784533c</email>
              <email type="domain">lri.fr</email>
              <idno type="idhal" notation="numeric">840508</idno>
              <idno type="halauthorid" notation="string">210136-840508</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=mdE4fyoAAAAJ</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-6031-0049</idno>
              <idno type="IDREF">https://www.idref.fr/156469073</idno>
              <affiliation ref="#struct-989"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Giorgio</forename>
                <surname>Ghelli</surname>
              </persName>
              <email type="md5">3b7ac2811ffce47b45e9aba0bec036bf</email>
              <email type="domain">di.unipi.it</email>
              <idno type="idhal" notation="numeric">1004291</idno>
              <idno type="halauthorid" notation="string">508739-1004291</idno>
              <affiliation ref="#struct-89633"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Carlo</forename>
                <surname>Sartiani</surname>
              </persName>
              <email type="md5">442529f94b161ae9191e1387c3f99348</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">1095200</idno>
              <idno type="halauthorid" notation="string">508740-1095200</idno>
              <affiliation ref="#struct-132915"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Mohamed-Amine</forename>
                <surname>Baazizi</surname>
              </persName>
              <email type="md5">a49d58f1bfaafd3ba167627d29382132</email>
              <email type="domain">lip6.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-05-01 11:40:04</date>
              <date type="whenModified">2025-06-13 11:38:14</date>
              <date type="whenReleased">2020-05-13 15:31:17</date>
              <date type="whenProduced">2020-03-30</date>
              <date type="whenEndEmbargoed">2020-05-01</date>
              <ref type="file" target="https://hal.science/hal-02560196v1/document">
                <date notBefore="2020-05-01"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02560196v1/file/paper-318.pdf" id="file-2560196-2426465">
                <date notBefore="2020-05-01"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="401378">
                <persName>
                  <forename>Mohamed-Amine</forename>
                  <surname>Baazizi</surname>
                </persName>
                <email type="md5">a49d58f1bfaafd3ba167627d29382132</email>
                <email type="domain">lip6.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02560196</idno>
            <idno type="halUri">https://hal.science/hal-02560196</idno>
            <idno type="halBibtex">baazizi:hal-02560196</idno>
            <idno type="halRefHtml">&lt;i&gt;EDBT 2020 - 23nd International Conference on Extending Database Technology&lt;/i&gt;, Mar 2020, Copenhagen, Denmark. pp.635-638, &lt;a target="_blank" href="https://dx.doi.org/10.5441/002/edbt.2020.82"&gt;&amp;#x27E8;10.5441/002/edbt.2020.82&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">EDBT 2020 - 23nd International Conference on Extending Database Technology, Mar 2020, Copenhagen, Denmark. pp.635-638, &amp;#x27E8;10.5441/002/edbt.2020.82&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2560196-2426465"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-DAUPHINE">Université Paris Dauphine - Paris IX</idno>
            <idno type="stamp" n="LIP6" corresp="SORBONNE-UNIVERSITE">Laboratoire d'Informatique de Paris 6</idno>
            <idno type="stamp" n="LAMSADE-DAUPHINE" corresp="UNIV-DAUPHINE">LAMSADE (Laboratoire d'Analyse et de Modélisation des Systèmes pour l'Aide à la Décision)</idno>
            <idno type="stamp" n="PSL">Université Paris sciences et lettres</idno>
            <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="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="UNIV-DAUPHINE-PSL" corresp="PSL">Université Paris Dauphine - PSL</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_MATHS_INFO">Mathématiques + Informatique</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">Human-in-the-Loop Schema Inference for Massive JSON Datasets</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Mohamed-Amine</forename>
                    <surname>Baazizi</surname>
                  </persName>
                  <email type="md5">a49d58f1bfaafd3ba167627d29382132</email>
                  <email type="domain">lip6.fr</email>
                  <idno type="idhal" notation="string">mohamed-amine-baazizi</idno>
                  <idno type="idhal" notation="numeric">13062</idno>
                  <idno type="halauthorid" notation="string">26388-13062</idno>
                  <idno type="IDREF">https://www.idref.fr/162548923</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2728-5838</idno>
                  <affiliation ref="#struct-541715"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Clément</forename>
                    <surname>Berti</surname>
                  </persName>
                  <email type="md5">2e1896bbae36c028b62309d34713c412</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">1068994</idno>
                  <idno type="halauthorid" notation="string">1836209-1068994</idno>
                  <affiliation ref="#struct-413221"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Dario</forename>
                    <surname>Colazzo</surname>
                  </persName>
                  <email type="md5">656cc7989e90a4924f1c484d5784533c</email>
                  <email type="domain">lri.fr</email>
                  <idno type="idhal" notation="numeric">840508</idno>
                  <idno type="halauthorid" notation="string">210136-840508</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=mdE4fyoAAAAJ</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-6031-0049</idno>
                  <idno type="IDREF">https://www.idref.fr/156469073</idno>
                  <affiliation ref="#struct-989"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Giorgio</forename>
                    <surname>Ghelli</surname>
                  </persName>
                  <email type="md5">3b7ac2811ffce47b45e9aba0bec036bf</email>
                  <email type="domain">di.unipi.it</email>
                  <idno type="idhal" notation="numeric">1004291</idno>
                  <idno type="halauthorid" notation="string">508739-1004291</idno>
                  <affiliation ref="#struct-89633"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Carlo</forename>
                    <surname>Sartiani</surname>
                  </persName>
                  <email type="md5">442529f94b161ae9191e1387c3f99348</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">1095200</idno>
                  <idno type="halauthorid" notation="string">508740-1095200</idno>
                  <affiliation ref="#struct-132915"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>EDBT 2020 - 23nd International Conference on Extending Database Technology</title>
                  <date type="start">2020-03-30</date>
                  <date type="end">2020-04-02</date>
                  <settlement>Copenhagen</settlement>
                  <country key="DK">Denmark</country>
                </meeting>
                <imprint>
                  <publisher>OpenProceedings.org</publisher>
                  <biblScope unit="pp">635-638</biblScope>
                </imprint>
              </monogr>
              <idno type="doi">10.5441/002/edbt.2020.82</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-db">Computer Science [cs]/Databases [cs.DB]</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>JSON established itself as a popular data format for representing data whose structure is irregular or unknown a priori. JSON collections are usually massive and schema-less. Inferring a schema describing the structure of these collections is crucial for formulating meaningful queries and for adopting schema-based optimizations. In a recent work, we proposed a Map/Reduce schema inference approach that either infers a compact representation of the input collection or a precise description of every possible shape in the data. Since no level of precision is ideal, it is more appealing to give the analyst the freedom of choosing between different levels of precisions in an interactive fashion. In this paper we describe a schema inference system offering this important functionality.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-541715" status="VALID">
          <orgName>Bases de Données</orgName>
          <orgName type="acronym">BD</orgName>
          <date type="start">2008-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-541703" type="direct"/>
            <relation active="#struct-413221" type="indirect"/>
            <relation name="UMR7606" active="#struct-441569" type="indirect"/>
          </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="laboratory" xml:id="struct-989" status="VALID">
          <idno type="IdRef">030107156</idno>
          <idno type="ISNI">0000 0001 2097 7052</idno>
          <idno type="RNSR">201120462Y</idno>
          <idno type="ROR">https://ror.org/052bz7812</idno>
          <idno type="Wikidata">Q3214405</idno>
          <orgName>Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision</orgName>
          <orgName type="acronym">LAMSADE</orgName>
          <desc>
            <address>
              <addrLine>Place de Lattre de Tassigny 75775 PARIS CEDEX 16</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lamsade.dauphine.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300302" type="direct"/>
            <relation active="#struct-564132" type="indirect"/>
            <relation name="UMR7243 / FRE3234 / UMR7024" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-89633" status="VALID">
          <orgName>Dipartimento di Informatica [Pisa]</orgName>
          <orgName type="acronym">DI</orgName>
          <desc>
            <address>
              <addrLine>University of Pisa Dipartimento di Informatica Largo B. Pontecorvo, 3 (formerly via F. Buonarroti, 2) I-56127 Pisa</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">http://www.di.unipi.it/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-366408" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-132915" status="VALID">
          <orgName>Dipartimento di Matematica e Informatica</orgName>
          <orgName type="acronym">DMI</orgName>
          <desc>
            <address>
              <addrLine>Dipartimento di Matematica e Informatica - Università degli Studi della Basilicata Viale Dell´Ateneo Lucano nº10, Macchia Romana - 85100, Potenza - Italy</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">http://pzmath.unibas.it/dmi/index.php</ref>
          </desc>
          <listRelation>
            <relation active="#struct-242534" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-541703" status="VALID">
          <idno type="IdRef">13558292X</idno>
          <idno type="RNSR">199712651U</idno>
          <idno type="ROR">https://ror.org/05krcen59</idno>
          <orgName>LIP6</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>4 Place JUSSIEU 75252 PARIS CEDEX 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lip6.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-413221" type="direct"/>
            <relation name="UMR7606" active="#struct-441569" type="direct"/>
          </listRelation>
        </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-300302" status="VALID">
          <idno type="IdRef">027787109</idno>
          <idno type="ISNI">0000000120977052</idno>
          <idno type="ROR">https://ror.org/052bz7812</idno>
          <idno type="Wikidata">Q1546437</idno>
          <orgName>Université Paris Dauphine-PSL</orgName>
          <desc>
            <address>
              <addrLine>Place du Maréchal de Lattre de Tassigny75775 PARIS Cedex 16</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://dauphine.psl.eu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-564132" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-564132" status="VALID">
          <idno type="IdRef">241597595</idno>
          <idno type="ISNI">0000 0004 1784 3645</idno>
          <idno type="ROR">https://ror.org/013cjyk83</idno>
          <orgName>Université Paris Sciences et Lettres</orgName>
          <orgName type="acronym">PSL</orgName>
          <desc>
            <address>
              <addrLine>60 rue Mazarine 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.psl.eu/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-366408" status="VALID">
          <idno type="IdRef">026619385</idno>
          <idno type="ISNI">0000000417573729</idno>
          <idno type="ROR">https://ror.org/03ad39j10</idno>
          <idno type="Wikidata">Q645663</idno>
          <orgName>University of Pisa [Italy] = Università di Pisa [Italia] = Université de Pise [Italie]</orgName>
          <orgName type="acronym">UniPi</orgName>
          <date type="start">1343-01-01</date>
          <desc>
            <address>
              <addrLine>Lungarno Pacinotti 43 – 56126 Pisa – Italia</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">https://www.unipi.it/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-242534" status="VALID">
          <idno type="ROR">https://ror.org/03tc05689</idno>
          <orgName>Università degli studi della Basilicata = University of Basilicata</orgName>
          <orgName type="acronym">UNIBAS</orgName>
          <desc>
            <address>
              <addrLine>Via Nazario Sauro 85 - 85100 Potenza</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">http://portale.unibas.it/site/home.html</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>