<?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-01987332</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="2026-05-15T14:24:34+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Linking and disambiguating entities across heterogeneous RDF graphs</title>
            <author role="aut">
              <persName>
                <forename type="first">Manel</forename>
                <surname>Achichi</surname>
              </persName>
              <idno type="halauthorid">1023643-0</idno>
              <affiliation ref="#struct-475163"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Zohra</forename>
                <surname>Bellahsene</surname>
              </persName>
              <email type="md5">1fa349bad174e06f69dc2df1883595bc</email>
              <email type="domain">lirmm.fr</email>
              <idno type="idhal" notation="string">zohra-bellahsene</idno>
              <idno type="idhal" notation="numeric">169913</idno>
              <idno type="halauthorid" notation="string">15690-169913</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2031-0519</idno>
              <idno type="IDREF">https://www.idref.fr/07917857X</idno>
              <affiliation ref="#struct-475163"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mohamed</forename>
                <surname>Ben Ellefi</surname>
              </persName>
              <email type="md5">ecdbb1550a58ab888c2f2dd76e72596f</email>
              <email type="domain">lirmm.fr</email>
              <idno type="idhal" notation="numeric">795352</idno>
              <idno type="halauthorid" notation="string">1088602-795352</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4458-0919</idno>
              <affiliation ref="#struct-527033"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Konstantin</forename>
                <surname>Todorov</surname>
              </persName>
              <email type="md5">a09893d062d78fc8541ac3b8adb27c88</email>
              <email type="domain">lirmm.fr</email>
              <idno type="idhal" notation="string">konstantin-todorov</idno>
              <idno type="idhal" notation="numeric">10784</idno>
              <idno type="halauthorid" notation="string">14023-10784</idno>
              <idno type="IDREF">https://www.idref.fr/226753247</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9116-6692</idno>
              <affiliation ref="#struct-475163"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Konstantin</forename>
                <surname>Todorov</surname>
              </persName>
              <email type="md5">a09893d062d78fc8541ac3b8adb27c88</email>
              <email type="domain">lirmm.fr</email>
            </editor>
            <funder ref="#projanr-41164"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2019-01-21 14:57:50</date>
              <date type="whenModified">2026-02-11 10:47:58</date>
              <date type="whenReleased">2019-02-05 18:10:51</date>
              <date type="whenProduced">2019-03</date>
              <date type="whenEndEmbargoed">2019-01-21</date>
              <ref type="file" target="https://hal.science/hal-01987332v1/document">
                <date notBefore="2019-01-21"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01987332v1/file/Linking_and_Disambiguating_Entities_Across_Heterogeneous_RDF_Graphs-2.pdf" id="file-1988050-2021370">
                <date notBefore="2019-01-21"/>
              </ref>
              <ref type="externalLink" target="https://hal.archives-ouvertes.fr/hal-01987332/file/Linking_and_Disambiguating_Entities_Across_Heterogeneous_RDF_Graphs-2.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="185424">
                <persName>
                  <forename>Konstantin</forename>
                  <surname>Todorov</surname>
                </persName>
                <email type="md5">a09893d062d78fc8541ac3b8adb27c88</email>
                <email type="domain">lirmm.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01987332</idno>
            <idno type="halUri">https://hal.science/hal-01987332</idno>
            <idno type="halBibtex">achichi:hal-01987332</idno>
            <idno type="halRefHtml">&lt;i&gt;Journal of Web Semantics&lt;/i&gt;, 2019, 55, pp.108-121. &lt;a target="_blank" href="https://dx.doi.org/10.1016/j.websem.2018.12.003"&gt;&amp;#x27E8;10.1016/j.websem.2018.12.003&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Journal of Web Semantics, 2019, 55, pp.108-121. &amp;#x27E8;10.1016/j.websem.2018.12.003&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1988050-2021370"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-TLN">Université de Toulon</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-AMU">Aix Marseille Université</idno>
            <idno type="stamp" n="LIRMM">Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier</idno>
            <idno type="stamp" n="OPENDATA">OPENDATA</idno>
            <idno type="stamp" n="MIPS">Mathématiques, Informatique, Physique et Systèmes</idno>
            <idno type="stamp" n="UNIV-MONTPELLIER">Université de Montpellier</idno>
            <idno type="stamp" n="ANR-DOREMUS">DOREMUS : Données en réutilisation dans le domaine de la musique en fonction des usages</idno>
            <idno type="stamp" n="ANR_BNF">Projets de la BnF financés par l'ANR</idno>
            <idno type="stamp" n="FADO" corresp="LIRMM">Fuzziness, Alignments, Data &amp; Ontologies</idno>
            <idno type="stamp" n="LIS-LAB">Laboratoire d'Informatique et Systèmes</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="UM-2015-2021" corresp="UNIV-MONTPELLIER">Université de Montpellier (2015-2021)</idno>
            <idno type="stamp" n="WEB3">WEB3</idno>
            <idno type="stamp" n="WEB-CUBE" corresp="LIRMM">WEB-CUBE</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">Linking and disambiguating entities across heterogeneous RDF graphs</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Manel</forename>
                    <surname>Achichi</surname>
                  </persName>
                  <idno type="halauthorid">1023643-0</idno>
                  <affiliation ref="#struct-475163"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Zohra</forename>
                    <surname>Bellahsene</surname>
                  </persName>
                  <email type="md5">1fa349bad174e06f69dc2df1883595bc</email>
                  <email type="domain">lirmm.fr</email>
                  <idno type="idhal" notation="string">zohra-bellahsene</idno>
                  <idno type="idhal" notation="numeric">169913</idno>
                  <idno type="halauthorid" notation="string">15690-169913</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2031-0519</idno>
                  <idno type="IDREF">https://www.idref.fr/07917857X</idno>
                  <affiliation ref="#struct-475163"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mohamed</forename>
                    <surname>Ben Ellefi</surname>
                  </persName>
                  <email type="md5">ecdbb1550a58ab888c2f2dd76e72596f</email>
                  <email type="domain">lirmm.fr</email>
                  <idno type="idhal" notation="numeric">795352</idno>
                  <idno type="halauthorid" notation="string">1088602-795352</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4458-0919</idno>
                  <affiliation ref="#struct-527033"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Konstantin</forename>
                    <surname>Todorov</surname>
                  </persName>
                  <email type="md5">a09893d062d78fc8541ac3b8adb27c88</email>
                  <email type="domain">lirmm.fr</email>
                  <idno type="idhal" notation="string">konstantin-todorov</idno>
                  <idno type="idhal" notation="numeric">10784</idno>
                  <idno type="halauthorid" notation="string">14023-10784</idno>
                  <idno type="IDREF">https://www.idref.fr/226753247</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9116-6692</idno>
                  <affiliation ref="#struct-475163"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">19880</idno>
                <idno type="issn">1570-8268</idno>
                <title level="j">Journal of Web Semantics</title>
                <imprint>
                  <publisher>Elsevier</publisher>
                  <biblScope unit="volume">55</biblScope>
                  <biblScope unit="pp">108-121</biblScope>
                  <date type="datePub">2019-03</date>
                  <date type="dateEpub">2019-01-02</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1016/j.websem.2018.12.003</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">RDF Data Linking</term>
                <term xml:lang="en">Data Heterogeneities</term>
                <term xml:lang="en">Knowledge Graphs</term>
                <term xml:lang="en">Linked Open Data</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-db">Computer Science [cs]/Databases [cs.DB]</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>Establishing identity links across RDF datasets is a central and challenging task on the way to realising the Data Web project. It is well-known that data supplied by different sources can be highly heterogeneous—two entities referring to the same real world object are often described, structured and valued differently, or in a complementary fashion. In this paper, we explore the origins and the multiplicity of data heterogeneity problems, proposing a novel classification that allows to isolate challenges and to position our and future work. Many state-of-the-art data linking approaches rely on sets of discriminative properties, provided by the user or by specialised tools, which, in the lack of knowledge of the nature of the data, do not allow to account automatically for a large number of structural heterogeneities. In addition, similarity measures and thresholds need to be selected and tuned manually or learned by specialised algorithms. We propose a solution covering an important number of heterogeneities, attempting to reduce the user configuration effort, based on: (i) Property filtering, or automatic data cleaning of “problematic” attributes; (ii) Instance profiling allowing to represent each resource by a sub-graph considered relevant for the comparison task; and (iii) Instance vector representation allowing to compare resources. To reduce the false positives rate, we apply a (iv) Post-processing step based on hierarchical clustering and key ranking techniques aiming to disambiguate highly similar, though not identical instances. This pipeline is implemented in Legato—a data linking tool, showing to outperform or to perform as well as state-of-the-art tools on highly heterogeneous and diverse benchmark datasets, yet keeping the user configuration effort low.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-475163" status="OLD">
          <orgName>WEB Architecture x Semantic WEB x WEB of Data</orgName>
          <orgName type="acronym">WEB3</orgName>
          <date type="start">2017-01-01</date>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>LIRMM, 161 rue Ada, 34000 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lirmm.fr/equipes/WEB3/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-181" type="direct"/>
            <relation name="UMR5506" active="#struct-410122" type="indirect"/>
            <relation name="UMR5506" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-527033" status="VALID">
          <idno type="IdRef">234768002</idno>
          <idno type="RNSR">201822714R</idno>
          <idno type="ROR">https://ror.org/0257sgk90</idno>
          <idno type="Wikidata">Q52605252</idno>
          <orgName>Laboratoire d'Informatique et des Systèmes (LIS) (Marseille, Toulon)</orgName>
          <orgName type="acronym">LIS</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>Aix Marseille Université – Campus de Saint Jérôme – Bat. Polytech, 52 Av. Escadrille Normandie Niemen, 13397 Marseille Cedex 20</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lis-lab.fr</ref>
          </desc>
          <listRelation>
            <relation name="UMR7020" active="#struct-198056" type="direct"/>
            <relation name="UMR7020" active="#struct-303091" type="direct"/>
            <relation name="UMR7020" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-181" status="OLD">
          <idno type="IdRef">139590827</idno>
          <idno type="ISNI">0000000405990488</idno>
          <idno type="RNSR">199111950H</idno>
          <idno type="ROR">https://ror.org/013yean28</idno>
          <orgName>Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier</orgName>
          <orgName type="acronym">LIRMM</orgName>
          <date type="start">1995-01-01</date>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>161 rue Ada - 34095 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lirmm.fr</ref>
          </desc>
          <listRelation>
            <relation name="UMR5506" active="#struct-410122" type="direct"/>
            <relation name="UMR5506" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-410122" status="OLD">
          <idno type="ISNI">0000000120970141</idno>
          <idno type="ROR">https://ror.org/051escj72</idno>
          <orgName>Université de Montpellier</orgName>
          <orgName type="acronym">UM</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>163 rue Auguste Broussonnet - 34090 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.umontpellier.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-198056" status="VALID">
          <idno type="IdRef">15863621X</idno>
          <idno type="ISNI">0000 0001 2176 4817</idno>
          <idno type="ROR">https://ror.org/035xkbk20</idno>
          <orgName>Aix Marseille Université</orgName>
          <orgName type="acronym">AMU</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Aix-Marseille UniversitéJardins du Pharo58 Boulevard Charles Livon13284 Marseille cedex 7</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-amu.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-303091" status="VALID">
          <idno type="IdRef">031122337</idno>
          <idno type="ROR">https://ror.org/02m9kbe37</idno>
          <orgName>Université de Toulon</orgName>
          <orgName type="acronym">UTLN</orgName>
          <desc>
            <address>
              <addrLine>Avenue de l'Université - BP 20132 - 83957 La Garde Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tln.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-41164" status="VALID">
          <idno type="anr">ANR-14-CE24-0020</idno>
          <idno type="program">Appel à projets générique</idno>
          <orgName>DOREMUS</orgName>
          <desc>Données en réutilisation dans le domaine de la musique en fonction des usages</desc>
          <date type="start">2014</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>