<?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-02612896</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="2026-05-14T01:34:11+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">The Missing Path: Diagnosing Incompleteness in Linked Data</title>
            <author role="aut">
              <persName>
                <forename type="first">Marie</forename>
                <surname>Destandau</surname>
              </persName>
              <email type="md5">b94abbce1530d0b3bb0ccb8e2189147c</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">marie-destandau</idno>
              <idno type="idhal" notation="numeric">184843</idno>
              <idno type="halauthorid" notation="string">47796-184843</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6911-2543</idno>
              <idno type="IDREF">https://www.idref.fr/253126460</idno>
              <affiliation ref="#struct-1062150"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jean-Daniel</forename>
                <surname>Fekete</surname>
              </persName>
              <email type="md5">6ad8d674f3d6c9920d3b667534f7f1ec</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">jean-daniel-fekete</idno>
              <idno type="idhal" notation="numeric">8723</idno>
              <idno type="halauthorid" notation="string">1777-8723</idno>
              <idno type="ARXIV">https://arxiv.org/a/fekete_j_1</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/N-9175-2018</idno>
              <idno type="IDREF">https://www.idref.fr/08305491X</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3770-8726</idno>
              <idno type="VIAF">https://viaf.org/viaf/220807935</idno>
              <idno type="ISNI">http://isni.org/isni/0000000360668419</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?hl=en&amp;user=PMZ3h7sAAAAJ</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/N-9175-2018</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-1062150"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Marie</forename>
                <surname>DESTANDAU</surname>
              </persName>
              <email type="md5">b94abbce1530d0b3bb0ccb8e2189147c</email>
              <email type="domain">inria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-05-19 16:42:23</date>
              <date type="whenModified">2025-10-24 16:40:04</date>
              <date type="whenReleased">2020-05-19 16:42:23</date>
              <date type="whenProduced">2021-02-22</date>
              <ref type="externalLink" target="http://arxiv.org/pdf/2005.08101"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="577161">
                <persName>
                  <forename>Marie</forename>
                  <surname>DESTANDAU</surname>
                </persName>
                <email type="md5">b94abbce1530d0b3bb0ccb8e2189147c</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02612896</idno>
            <idno type="halUri">https://hal.science/hal-02612896</idno>
            <idno type="halBibtex">destandau:hal-02612896</idno>
            <idno type="halRefHtml">&lt;i&gt;Information Visualization&lt;/i&gt;, 2021, 20 (1), pp.66-82. &lt;a target="_blank" href="https://dx.doi.org/10.1177/1473871621991539"&gt;&amp;#x27E8;10.1177/1473871621991539&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Information Visualization, 2021, 20 (1), pp.66-82. &amp;#x27E8;10.1177/1473871621991539&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="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-SACLAY" corresp="INRIA">INRIA Saclay - Ile de France</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="INRIA-300009">Inria 300009</idno>
            <idno type="stamp" n="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="LISN">Laboratoire Interdisciplinaire des Sciences du Numérique</idno>
            <idno type="stamp" n="GS-ENGINEERING">Graduate School Sciences de l'Ingénierie et des Systèmes</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="LISN-AVIZ" corresp="LISN">Analysis and Visualization </idno>
            <idno type="stamp" n="INRIA_WEB">Inria &amp; web</idno>
            <idno type="stamp" n="INRIAARTDOI">INRIAARTDOI</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">The Missing Path: Diagnosing Incompleteness in Linked Data</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Marie</forename>
                    <surname>Destandau</surname>
                  </persName>
                  <email type="md5">b94abbce1530d0b3bb0ccb8e2189147c</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">marie-destandau</idno>
                  <idno type="idhal" notation="numeric">184843</idno>
                  <idno type="halauthorid" notation="string">47796-184843</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6911-2543</idno>
                  <idno type="IDREF">https://www.idref.fr/253126460</idno>
                  <affiliation ref="#struct-1062150"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jean-Daniel</forename>
                    <surname>Fekete</surname>
                  </persName>
                  <email type="md5">6ad8d674f3d6c9920d3b667534f7f1ec</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">jean-daniel-fekete</idno>
                  <idno type="idhal" notation="numeric">8723</idno>
                  <idno type="halauthorid" notation="string">1777-8723</idno>
                  <idno type="ARXIV">https://arxiv.org/a/fekete_j_1</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/N-9175-2018</idno>
                  <idno type="IDREF">https://www.idref.fr/08305491X</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3770-8726</idno>
                  <idno type="VIAF">https://viaf.org/viaf/220807935</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000360668419</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?hl=en&amp;user=PMZ3h7sAAAAJ</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/N-9175-2018</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-1062150"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">14200</idno>
                <idno type="issn">1473-8716</idno>
                <idno type="eissn">1473-8724</idno>
                <title level="j">Information Visualization</title>
                <imprint>
                  <publisher>SAGE Publications</publisher>
                  <biblScope unit="volume">20</biblScope>
                  <biblScope unit="issue">1</biblScope>
                  <biblScope unit="pp">66-82</biblScope>
                  <date type="datePub">2021-02-22</date>
                </imprint>
              </monogr>
              <idno type="arxiv">2005.08101</idno>
              <idno type="doi">10.1177/1473871621991539</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Semantic Web</term>
                <term xml:lang="en">Completeness</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-hc">Computer Science [cs]/Human-Computer Interaction [cs.HC]</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>The Semantic Web is an interoperable ecosystem where data producers, such as libraries, public institutions, communities, and companies, publish and link heterogeneous resources. To support this heterogeneity, its format, RDF, allows to describe collections of items sharing some attributes but not necessarily all of them. This flexible framework leads to incompleteness and inconsistencies in information representation, which in turn leads to unreliable query results. In order to make their data reliable and usable, Linked Data producers need to provide the best level of completeness. We propose a novel visualization tool "The Missing Path" to support data producers in diagnosing incompleteness in their data. It relies on dimensional reduction techniques to create a map of RDF entities based on missing paths, revealing clusters of entities missing the same paths. The novelty of our work consists in describing the entities of interest as vectors of aggregated RDF paths of a fixed length. We show that identifying groups of items sharing a similar structure helps users find the cause of incompleteness for entire groups and allows them to decide if and how it has to be resolved. We describe our iterative design process and evaluation with Wikidata contributors.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1062150" status="VALID">
          <idno type="RNSR">200818367J</idno>
          <idno type="ROR">https://ror.org/01z2f0n71</idno>
          <orgName>Analysis and Visualization</orgName>
          <orgName type="acronym">AVIZ</orgName>
          <date type="start">2021-01-01</date>
          <date type="end">2028-06-30</date>
          <desc>
            <address>
              <addrLine>DIGITEO, Bât. Claude Shannon - Université Paris-Saclay, Bâtiment 660, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://aviz.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1061259" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-419361" type="indirect"/>
            <relation name="UMR9015" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1065374" type="direct"/>
            <relation active="#struct-1225627" type="direct"/>
            <relation active="#struct-118511" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1061259" status="VALID">
          <idno type="IdRef">253160316</idno>
          <idno type="RNSR">202123711L</idno>
          <idno type="ROR">https://ror.org/00rd81916</idno>
          <idno type="Wikidata">Q109620676</idno>
          <orgName>Laboratoire Interdisciplinaire des Sciences du Numérique</orgName>
          <orgName type="acronym">LISN</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Universitaire bât 507Rue du Belvédère91405 Orsay cedexet Campus Universitaire bât 6401 rue Raimond Castaing91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lisn.upsaclay.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UMR9015" 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-419361" status="VALID">
          <idno type="IdRef">241345251</idno>
          <idno type="ROR">https://ror.org/03xjwb503</idno>
          <orgName>Université Paris-Saclay</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Bréguet, 3 Rue Joliot Curie 2e ét, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/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="department" xml:id="struct-1065374" status="VALID">
          <orgName>Interaction avec l'Humain</orgName>
          <orgName type="acronym">IaH</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1061259" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-419361" type="indirect"/>
            <relation name="UMR9015" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="department" xml:id="struct-1225627" status="VALID">
          <idno type="ROR">https://ror.org/040753f36</idno>
          <orgName>Centre Inria de l'Université Paris-Saclay</orgName>
          <date type="start">2022-11-01</date>
          <desc>
            <address>
              <addrLine>9 Rue Joliot Curie, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-118511" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-118511" status="VALID">
          <idno type="RNSR">200818248E</idno>
          <idno type="ROR">https://ror.org/0315e5x55</idno>
          <orgName>Centre Inria de Saclay</orgName>
          <desc>
            <address>
              <addrLine>1 rue Honoré d'Estienne d'OrvesBâtiment Alan TuringCampus de l'École Polytechnique91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/saclay</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>