<?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-04273080</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="2026-05-02T09:46:58+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A semantic and service-based approach for adaptive mutli-structured data curation in data lakehouses</title>
            <author role="aut">
              <persName>
                <forename type="first">Firas</forename>
                <surname>Zouari</surname>
              </persName>
              <email type="md5">48cccb0f1432987cf8c05cbeec2806e1</email>
              <email type="domain">univ-lyon3.fr</email>
              <idno type="idhal" notation="string">firas-zouari</idno>
              <idno type="idhal" notation="numeric">748347</idno>
              <idno type="halauthorid" notation="string">54515-748347</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6403-2157</idno>
              <idno type="IDREF">https://www.idref.fr/278667481</idno>
              <affiliation ref="#struct-393309"/>
              <affiliation ref="#struct-2003"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Chirine</forename>
                <surname>Ghedira-Guegan</surname>
              </persName>
              <email type="md5">c698f6fede766053b2a39d755683aa44</email>
              <email type="domain">univ-lyon3.fr</email>
              <idno type="idhal" notation="string">chirine-ghedira</idno>
              <idno type="idhal" notation="numeric">5354</idno>
              <idno type="halauthorid" notation="string">839158-5354</idno>
              <idno type="IDREF">https://www.idref.fr/083803467</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0908-2711</idno>
              <idno type="ISNI">http://isni.org/isni/0000000357248413</idno>
              <idno type="VIAF">https://viaf.org/viaf/194974765</idno>
              <affiliation ref="#struct-393309"/>
              <affiliation ref="#struct-2003"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Khouloud</forename>
                <surname>Boukadi</surname>
              </persName>
              <idno type="idhal" notation="numeric">1246445</idno>
              <idno type="halauthorid" notation="string">370266-1246445</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-6744-711X</idno>
              <affiliation ref="#struct-303396"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nadia</forename>
                <surname>Kabachi</surname>
              </persName>
              <idno type="idhal" notation="numeric">1304004</idno>
              <idno type="halauthorid" notation="string">249632-1304004</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-8071-8490</idno>
              <affiliation ref="#struct-194495"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Chirine</forename>
                <surname>Ghedira</surname>
              </persName>
              <email type="md5">c698f6fede766053b2a39d755683aa44</email>
              <email type="domain">univ-lyon3.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-11-07 09:34:13</date>
              <date type="whenWritten">2023</date>
              <date type="whenModified">2025-12-03 01:47:00</date>
              <date type="whenReleased">2023-11-07 09:34:13</date>
              <date type="whenProduced">2023-11</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="181614">
                <persName>
                  <forename>Chirine</forename>
                  <surname>Ghedira</surname>
                </persName>
                <email type="md5">c698f6fede766053b2a39d755683aa44</email>
                <email type="domain">univ-lyon3.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04273080</idno>
            <idno type="halUri">https://hal.science/hal-04273080</idno>
            <idno type="halBibtex">zouari:hal-04273080</idno>
            <idno type="halRefHtml">&lt;i&gt;World Wide Web&lt;/i&gt;, 2023, pp.4001-4023. &lt;a target="_blank" href="https://dx.doi.org/10.1007/s11280-023-01218-3"&gt;&amp;#x27E8;10.1007/s11280-023-01218-3&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">World Wide Web, 2023, pp.4001-4023. &amp;#x27E8;10.1007/s11280-023-01218-3&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-LYON1">Université Claude Bernard - Lyon I</idno>
            <idno type="stamp" n="UNIV-LYON2">Université Lumière Lyon 2</idno>
            <idno type="stamp" n="INSA-LYON">Institut National des Sciences Appliquées de Lyon</idno>
            <idno type="stamp" n="EC-LYON">Ecole Centrale de Lyon</idno>
            <idno type="stamp" n="LIRIS" corresp="UNIV-LYON1">Laboratoire d'InfoRmatique en Image et Systèmes d'information</idno>
            <idno type="stamp" n="LYON2">Université Lyon2</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="HAL-LYON-2-NOUVELLE-VERSION">Nouvelle version portail </idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">A semantic and service-based approach for adaptive mutli-structured data curation in data lakehouses</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Firas</forename>
                    <surname>Zouari</surname>
                  </persName>
                  <email type="md5">48cccb0f1432987cf8c05cbeec2806e1</email>
                  <email type="domain">univ-lyon3.fr</email>
                  <idno type="idhal" notation="string">firas-zouari</idno>
                  <idno type="idhal" notation="numeric">748347</idno>
                  <idno type="halauthorid" notation="string">54515-748347</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6403-2157</idno>
                  <idno type="IDREF">https://www.idref.fr/278667481</idno>
                  <affiliation ref="#struct-393309"/>
                  <affiliation ref="#struct-2003"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Chirine</forename>
                    <surname>Ghedira-Guegan</surname>
                  </persName>
                  <email type="md5">c698f6fede766053b2a39d755683aa44</email>
                  <email type="domain">univ-lyon3.fr</email>
                  <idno type="idhal" notation="string">chirine-ghedira</idno>
                  <idno type="idhal" notation="numeric">5354</idno>
                  <idno type="halauthorid" notation="string">839158-5354</idno>
                  <idno type="IDREF">https://www.idref.fr/083803467</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0908-2711</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000357248413</idno>
                  <idno type="VIAF">https://viaf.org/viaf/194974765</idno>
                  <affiliation ref="#struct-393309"/>
                  <affiliation ref="#struct-2003"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Khouloud</forename>
                    <surname>Boukadi</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1246445</idno>
                  <idno type="halauthorid" notation="string">370266-1246445</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-6744-711X</idno>
                  <affiliation ref="#struct-303396"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nadia</forename>
                    <surname>Kabachi</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1304004</idno>
                  <idno type="halauthorid" notation="string">249632-1304004</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-8071-8490</idno>
                  <affiliation ref="#struct-194495"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">19928</idno>
                <idno type="issn">1386-145X</idno>
                <idno type="eissn">1573-1413</idno>
                <title level="j">World Wide Web</title>
                <imprint>
                  <publisher>Springer Verlag</publisher>
                  <biblScope unit="pp">4001-4023</biblScope>
                  <date type="datePub">2023-11</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/s11280-023-01218-3</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Dynamic Service Composition</term>
                <term xml:lang="en">Data curation</term>
                <term xml:lang="en">· Machine Learning</term>
                <term xml:lang="en">· Reinforcement Learning</term>
                <term xml:lang="en">Data Lakehouse</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="info.info-et">Computer Science [cs]/Emerging Technologies [cs.ET]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Recently, we noticed the emergence of several data management architectures to cope with the challenges imposed by big data. Among them, data lakehouses are receiving much interest from industrial and academic ﬁelds due to their ability to hold disparate multi-structured batch and streaming data sources in a single data repository. Thus, the heterogeneous and complex aspect of the data requires a dedicated process to improve their quality and retrieve value from them. Therefore, data curation encompasses several tasks that clean and enrich data to ensure it continues to ﬁt the user requirements. Nevertheless, most existing data curation approaches need more dynamics, ﬂexibility, and customization in constituting the data curation pipeline to align with end-user requirements that may vary according to her/his decision context. Moreover, they are dedicated to curating only a single type of structure of batch data sources (e.g., semi-structured). Considering the changing requirements of the user and the need to build a customized data curation pipeline according to the users and the data source characteristics, we propose a service-based framework for adaptive data curation in data lakehouses that encompasses ﬁve modules: data collection, data quality evaluation, data characterization, curation service composition, and data curation. The proposed framework is built upon new data characterization and evaluation modular ontology and a curation service composition approach that we detail in the following paper. The experimental ﬁndingsvalidate the contributions’ performance in terms of effectiveness and execution time.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-393309" status="VALID">
          <orgName>Service Oriented Computing</orgName>
          <orgName type="acronym">SOC</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-2003" type="direct"/>
            <relation active="#struct-33804" type="indirect"/>
            <relation active="#struct-126765" type="indirect"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="indirect"/>
            <relation active="#struct-219748" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2003" status="VALID">
          <idno type="IdRef">149705271</idno>
          <idno type="ISNI">0000000122577669</idno>
          <idno type="RNSR">200511875R</idno>
          <idno type="ROR">https://ror.org/04dv4he91</idno>
          <orgName>Laboratoire d'InfoRmatique en Image et Systèmes d'information</orgName>
          <orgName type="acronym">LIRIS</orgName>
          <date type="start">2003-01-01</date>
          <desc>
            <address>
              <addrLine>Bâtiment Blaise Pascal - 20, avenue Albert Einstein - 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://liris.cnrs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-33804" type="direct"/>
            <relation active="#struct-126765" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="direct"/>
            <relation active="#struct-219748" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-303396" status="VALID">
          <idno type="IdRef">109165470</idno>
          <idno type="ISNI">0000000123235644</idno>
          <idno type="ROR">https://ror.org/04d4sd432</idno>
          <idno type="Wikidata">Q540341</idno>
          <orgName>جامعة صفاقس - Université de Sfax - University of Sfax</orgName>
          <date type="start">1986-01-01</date>
          <desc>
            <address>
              <addrLine>Route de l'Aéroport Km 0.5 - BP 1169 .3029 Sfax</addrLine>
              <country key="TN"/>
            </address>
            <ref type="url">http://univ-sfax.tn/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-194495" status="VALID">
          <idno type="IdRef">026402823</idno>
          <idno type="ISNI">0000000121686185</idno>
          <idno type="ROR">https://ror.org/029brtt94</idno>
          <orgName>Université Claude Bernard Lyon 1</orgName>
          <orgName type="acronym">UCBL</orgName>
          <desc>
            <address>
              <addrLine>43, boulevard du 11 novembre 1918, 69622 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-33804" status="VALID">
          <idno type="IdRef">02640334X</idno>
          <idno type="ISNI">0000 0001 2188 0906</idno>
          <idno type="ROR">https://ror.org/03rth4p18</idno>
          <idno type="Wikidata">Q4041</idno>
          <orgName>Université Lumière - Lyon 2</orgName>
          <orgName type="acronym">UL2</orgName>
          <desc>
            <address>
              <addrLine>86, rue Pasteur - 69007 Lyon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon2.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-126765" status="VALID">
          <idno type="ROR">https://ror.org/05s6rge65</idno>
          <orgName>École Centrale de Lyon</orgName>
          <orgName type="acronym">ECL</orgName>
          <desc>
            <address>
              <addrLine>36 avenue Guy de Collongue - 69134 Ecully cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ec-lyon.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301088" status="VALID">
          <idno type="ROR">https://ror.org/01rk35k63</idno>
          <orgName>Université de Lyon</orgName>
          <desc>
            <address>
              <addrLine>92 rue Pasteur - CS 30122, 69361 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-lyon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-219748" status="VALID">
          <idno type="IdRef">052444724</idno>
          <idno type="ISNI">0000 0001 2292 0228</idno>
          <orgName>Institut National des Sciences Appliquées de Lyon</orgName>
          <orgName type="acronym">INSA Lyon</orgName>
          <date type="start">1957-03-18</date>
          <desc>
            <address>
              <addrLine>20 Avenue Albert Einstein, 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-lyon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
            <relation active="#struct-301232" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </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>
    </back>
  </text>
</TEI>