<?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-03145214</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="2026-05-04T18:31:57+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">KEFT: Knowledge Extraction and Graph Building from Statistical Data Tables</title>
            <author role="aut">
              <persName>
                <forename type="first">Rabia</forename>
                <surname>Azzi</surname>
              </persName>
              <idno type="halauthorid">1398638-0</idno>
              <affiliation ref="#struct-476572"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sylvie</forename>
                <surname>Despres</surname>
              </persName>
              <email type="md5">9e6bebc87e1c8c93b6d86543662f4c9e</email>
              <email type="domain">lipn.univ-paris13.fr</email>
              <idno type="idhal" notation="string">sylvie-despres</idno>
              <idno type="idhal" notation="numeric">1015228</idno>
              <idno type="halauthorid" notation="string">216462-1015228</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0419-8312</idno>
              <affiliation ref="#struct-1001042"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gayo</forename>
                <surname>Diallo</surname>
              </persName>
              <email type="md5">bad8658f68b5d9a01db35e498fdabdfc</email>
              <email type="domain">u-bordeaux.fr</email>
              <idno type="idhal" notation="string">gayo-diallo</idno>
              <idno type="idhal" notation="numeric">3812</idno>
              <idno type="halauthorid" notation="string">23520-3812</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9799-9484</idno>
              <idno type="IDREF">https://www.idref.fr/112800084</idno>
              <affiliation ref="#struct-219689"/>
              <affiliation ref="#struct-476572"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Gayo</forename>
                <surname>Diallo</surname>
              </persName>
              <email type="md5">bad8658f68b5d9a01db35e498fdabdfc</email>
              <email type="domain">u-bordeaux.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-02-18 11:02:04</date>
              <date type="whenModified">2025-12-03 14:52:02</date>
              <date type="whenReleased">2021-02-18 11:02:04</date>
              <date type="whenProduced">2020-11-19</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="111147">
                <persName>
                  <forename>Gayo</forename>
                  <surname>Diallo</surname>
                </persName>
                <email type="md5">bad8658f68b5d9a01db35e498fdabdfc</email>
                <email type="domain">u-bordeaux.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03145214</idno>
            <idno type="halUri">https://hal.science/hal-03145214</idno>
            <idno type="halBibtex">azzi:hal-03145214</idno>
            <idno type="halRefHtml">Marcin Hernes; Krystian Wojtkiewicz; Edward Szczerbicki. &lt;i&gt;Communications in Computer and Information Science&lt;/i&gt;, 1287, Springer, pp.701-713, 2020, CCIS - Communications in Computer and Information Science, &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-030-63119-2_57"&gt;&amp;#x27E8;10.1007/978-3-030-63119-2_57&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Marcin Hernes; Krystian Wojtkiewicz; Edward Szczerbicki. Communications in Computer and Information Science, 1287, Springer, pp.701-713, 2020, CCIS - Communications in Computer and Information Science, &amp;#x27E8;10.1007/978-3-030-63119-2_57&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-PARIS13">Université Paris-Nord - Paris XIII </idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-BORDEAUX">INRIA Bordeaux - Sud-Ouest</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="LIMICS" corresp="SORBONNE-UNIVERSITE">Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="USPC">Université Sorbonne Paris Cité</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="SORBONNE-PARIS-NORD">Université Sorbonne Paris Nord</idno>
            <idno type="stamp" n="U1219" corresp="INSERM">Bordeaux Population Health</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="ACT-R" corresp="UNIV-PARIS13">Act'R </idno>
            <idno type="stamp" n="SUPRA_INGENIERIE">Ingénierie</idno>
            <idno type="stamp" n="UNIVERSITE-BORDEAUX">Université de Bordeaux</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">KEFT: Knowledge Extraction and Graph Building from Statistical Data Tables</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Rabia</forename>
                    <surname>Azzi</surname>
                  </persName>
                  <idno type="halauthorid">1398638-0</idno>
                  <affiliation ref="#struct-476572"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sylvie</forename>
                    <surname>Despres</surname>
                  </persName>
                  <email type="md5">9e6bebc87e1c8c93b6d86543662f4c9e</email>
                  <email type="domain">lipn.univ-paris13.fr</email>
                  <idno type="idhal" notation="string">sylvie-despres</idno>
                  <idno type="idhal" notation="numeric">1015228</idno>
                  <idno type="halauthorid" notation="string">216462-1015228</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0419-8312</idno>
                  <affiliation ref="#struct-1001042"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gayo</forename>
                    <surname>Diallo</surname>
                  </persName>
                  <email type="md5">bad8658f68b5d9a01db35e498fdabdfc</email>
                  <email type="domain">u-bordeaux.fr</email>
                  <idno type="idhal" notation="string">gayo-diallo</idno>
                  <idno type="idhal" notation="numeric">3812</idno>
                  <idno type="halauthorid" notation="string">23520-3812</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9799-9484</idno>
                  <idno type="IDREF">https://www.idref.fr/112800084</idno>
                  <affiliation ref="#struct-219689"/>
                  <affiliation ref="#struct-476572"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Communications in Computer and Information Science</title>
                <editor>Marcin Hernes</editor>
                <editor>Krystian Wojtkiewicz</editor>
                <editor>Edward Szczerbicki</editor>
                <imprint>
                  <publisher>Springer</publisher>
                  <biblScope unit="serie">CCIS - Communications in Computer and Information Science</biblScope>
                  <biblScope unit="volume">1287</biblScope>
                  <biblScope unit="pp">701-713</biblScope>
                  <date type="datePub">2020-11-19</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-030-63119-2_57</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">PDF document</term>
                <term xml:lang="en">Table recognition</term>
                <term xml:lang="en">Knowledge graph</term>
                <term xml:lang="en">Information extraction</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halTypology" n="COUV">Book sections</classCode>
              <classCode scheme="halOldTypology" n="COUV">Book sections</classCode>
              <classCode scheme="halTreeTypology" n="COUV">Book sections</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Data provided by statistical models are commonly represented by textual, tabular or graphical form in documents (reports, articles, posters and presentations). These documents are often available in PDF format. Even though it makes accessing a particular information more difficult, it is interesting to process the PDF documents directly. We present KEFT, a solution in the statistical domain and we describe the fully functional pipeline to constructing a knowledge graph by extracting entities and relations from statistical Data Tables. We showcase how this approach can be used to construct a knowledge graph from different statistical studies.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-476572" status="VALID">
          <idno type="IdRef">197398162</idno>
          <idno type="RNSR">201622170H</idno>
          <idno type="ROR">https://ror.org/00xzzba89</idno>
          <orgName>Bordeaux population health</orgName>
          <orgName type="acronym">BPH</orgName>
          <desc>
            <address>
              <addrLine>Université de Bordeaux - Case 11 - 146 rue Léo Saignat  33076 Bordeaux cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-259761" type="direct"/>
            <relation active="#struct-302259" type="direct"/>
            <relation name="U1219" active="#struct-303623" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1001042" status="VALID">
          <idno type="IdRef">190100990</idno>
          <idno type="RNSR">201420870D</idno>
          <idno type="ROR">https://ror.org/01jr1v359</idno>
          <orgName>Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé</orgName>
          <orgName type="acronym">LIMICS</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Campus des Cordeliers/Escalier D - 15 rue de l'Ecole de Médecine 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ics.upmc.fr/</ref>
          </desc>
          <listRelation>
            <relation name="U1142" active="#struct-303623" type="direct"/>
            <relation name="UMRS_1142" active="#struct-413221" type="direct"/>
            <relation active="#struct-581146" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-219689" status="VALID">
          <idno type="RNSR">201321095C</idno>
          <idno type="ROR">https://ror.org/026t7px13</idno>
          <orgName>Statistics In System biology and Translational Medicine</orgName>
          <orgName type="acronym">SISTM</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2027-12-31</date>
          <desc>
            <address>
              <addrLine>200, avenue de la Vieille Tour 33405 Talence cedex 146 Rue Léo Saignat33076 Bordeaux cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/sistm</ref>
          </desc>
          <listRelation>
            <relation active="#struct-104751" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-476572" type="direct"/>
            <relation active="#struct-259761" type="indirect"/>
            <relation active="#struct-302259" type="indirect"/>
            <relation name="U1219" active="#struct-303623" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-259761" status="VALID">
          <idno type="IdRef">175206562</idno>
          <idno type="ROR">https://ror.org/057qpr032</idno>
          <orgName>Université de Bordeaux</orgName>
          <orgName type="acronym">UB</orgName>
          <desc>
            <address>
              <addrLine>35, place Pey Berland - 33076 Bordeaux</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-bordeaux.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-302259" status="VALID">
          <orgName>Institut de Santé Publique, d'Épidémiologie et de Développement (ISPED)</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-303623" status="VALID">
          <idno type="IdRef">026388278</idno>
          <idno type="ROR">https://ror.org/02vjkv261</idno>
          <orgName>Institut National de la Santé et de la Recherche Médicale</orgName>
          <orgName type="acronym">INSERM</orgName>
          <desc>
            <address>
              <addrLine>101, rue de Tolbiac, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inserm.fr</ref>
          </desc>
        </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="institution" xml:id="struct-581146" status="VALID">
          <idno type="IdRef">02640463X</idno>
          <idno type="ISNI">0000000121496883</idno>
          <idno type="ROR">https://ror.org/0199hds37</idno>
          <orgName>Université Sorbonne Paris Nord</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>99, avenue Jean-Baptiste Clément, 93430 Villetaneuse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-paris13.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-104751" status="VALID">
          <idno type="RNSR">200818243Z</idno>
          <idno type="ROR">https://ror.org/03tjcj052</idno>
          <orgName>Centre Inria de l'Université de Bordeaux</orgName>
          <desc>
            <address>
              <addrLine>200, avenue de la Vieille Tour, 33405 Talence</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/bordeaux/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" 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>
      </listOrg>
    </back>
  </text>
</TEI>