<?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-01981922v3</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="2026-05-18T12:10:23+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Leveraging Concepts in Open Access Publications</title>
            <author role="aut">
              <persName>
                <forename type="first">Andrea</forename>
                <surname>Bertino</surname>
              </persName>
              <email type="md5">43c6e47d10a9ab0dce7aa7e96ce47786</email>
              <email type="domain">sub.uni-goettingen.de</email>
              <idno type="idhal" notation="string">andrea-bertino</idno>
              <idno type="idhal" notation="numeric">173442</idno>
              <idno type="halauthorid" notation="string">41887-173442</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5080-036X</idno>
              <affiliation ref="#struct-203762"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Luca</forename>
                <surname>Foppiano</surname>
              </persName>
              <email type="md5">5d7dfa79907f7bf28fb2f6680c94e0f6</email>
              <email type="domain">foppiano.org</email>
              <idno type="idhal" notation="string">luca-foppiano</idno>
              <idno type="idhal" notation="numeric">16134</idno>
              <idno type="halauthorid" notation="string">34995-16134</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-6114-6164</idno>
              <idno type="IDREF">https://www.idref.fr/253122546</idno>
              <affiliation ref="#struct-482775"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Laurent</forename>
                <surname>Romary</surname>
              </persName>
              <email type="md5">16ede816252b162dcca0da9d3409b614</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">laurentromary</idno>
              <idno type="idhal" notation="numeric">307</idno>
              <idno type="halauthorid" notation="string">3061-307</idno>
              <idno type="ARXIV">https://arxiv.org/a/romary_l_1</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/A-5114-2012</idno>
              <idno type="IDREF">https://www.idref.fr/060702494</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0756-0508</idno>
              <idno type="VIAF">https://viaf.org/viaf/282014122</idno>
              <idno type="ISNI">http://isni.org/isni/0000000388795444</idno>
              <affiliation ref="#struct-482775"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Pierre</forename>
                <surname>Mounier</surname>
              </persName>
              <email type="md5">4956155e6f8f80388e797ce0a2c7397f</email>
              <email type="domain">numericat.net</email>
              <idno type="idhal" notation="string">pierre-mounier</idno>
              <idno type="idhal" notation="numeric">357</idno>
              <idno type="halauthorid" notation="string">1405-357</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0691-6063</idno>
              <idno type="IDREF">https://www.idref.fr/050447823</idno>
              <affiliation ref="#struct-84824"/>
              <affiliation ref="#struct-99539"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Andrea</forename>
                <surname>Bertino</surname>
              </persName>
              <email type="md5">43c6e47d10a9ab0dce7aa7e96ce47786</email>
              <email type="domain">sub.uni-goettingen.de</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2019-01-15 12:29:05</date>
            </edition>
            <edition n="v2">
              <date type="whenSubmitted">2019-03-23 21:06:28</date>
            </edition>
            <edition n="v3" type="current">
              <date type="whenSubmitted">2019-03-25 10:28:45</date>
              <date type="whenModified">2026-04-05 14:22:02</date>
              <date type="whenReleased">2019-03-25 10:42:08</date>
              <date type="whenProduced">2020-06-15</date>
              <date type="whenEndEmbargoed">2019-03-25</date>
              <ref type="file" target="https://inria.hal.science/hal-01981922v3/document">
                <date notBefore="2019-03-25"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-01981922v3/file/Leveraging%20Concepts%20in%20Open%20Access%20Publications-2.%20Version%20edited%2003.2019.pdf" id="file-2078195-2078557">
                <date notBefore="2019-03-25"/>
              </ref>
              <ref type="externalLink" target="https://jdmdh.episciences.org/5303/pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="685035">
                <persName>
                  <forename>Andrea</forename>
                  <surname>Bertino</surname>
                </persName>
                <email type="md5">43c6e47d10a9ab0dce7aa7e96ce47786</email>
                <email type="domain">sub.uni-goettingen.de</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01981922</idno>
            <idno type="halUri">https://inria.hal.science/hal-01981922</idno>
            <idno type="halBibtex">bertino:hal-01981922</idno>
            <idno type="halRefHtml">&lt;i&gt;Journal of Data Mining and Digital Humanities&lt;/i&gt;, 2020, 2019, &lt;a target="_blank" href="https://dx.doi.org/10.46298/jdmdh.5081"&gt;&amp;#x27E8;10.46298/jdmdh.5081&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Journal of Data Mining and Digital Humanities, 2020, 2019, &amp;#x27E8;10.46298/jdmdh.5081&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2078195-2078557"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-AVIGNON">Université d'Avignon</idno>
            <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="UNIV-AMU">Aix Marseille Université</idno>
            <idno type="stamp" n="EHESS">Ecole des Hautes Etudes en Sciences Sociales</idno>
            <idno type="stamp" n="INRIA-ROCQ">INRIA Paris - Rocquencourt</idno>
            <idno type="stamp" n="CMB">Centre Marc Bloch</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="DARIAH">DARIAH - Digital Research Infrastructure for the Arts and Humanities</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="OPENEDITION">OPENEDITION</idno>
            <idno type="stamp" n="INRIAARTDOI">INRIAARTDOI</idno>
            <idno type="stamp" n="INRIA-ALLEMAGNE">INRIA-ALLEMAGNE</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">Leveraging Concepts in Open Access Publications</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Andrea</forename>
                    <surname>Bertino</surname>
                  </persName>
                  <email type="md5">43c6e47d10a9ab0dce7aa7e96ce47786</email>
                  <email type="domain">sub.uni-goettingen.de</email>
                  <idno type="idhal" notation="string">andrea-bertino</idno>
                  <idno type="idhal" notation="numeric">173442</idno>
                  <idno type="halauthorid" notation="string">41887-173442</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5080-036X</idno>
                  <affiliation ref="#struct-203762"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Luca</forename>
                    <surname>Foppiano</surname>
                  </persName>
                  <email type="md5">5d7dfa79907f7bf28fb2f6680c94e0f6</email>
                  <email type="domain">foppiano.org</email>
                  <idno type="idhal" notation="string">luca-foppiano</idno>
                  <idno type="idhal" notation="numeric">16134</idno>
                  <idno type="halauthorid" notation="string">34995-16134</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-6114-6164</idno>
                  <idno type="IDREF">https://www.idref.fr/253122546</idno>
                  <affiliation ref="#struct-482775"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Laurent</forename>
                    <surname>Romary</surname>
                  </persName>
                  <email type="md5">16ede816252b162dcca0da9d3409b614</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">laurentromary</idno>
                  <idno type="idhal" notation="numeric">307</idno>
                  <idno type="halauthorid" notation="string">3061-307</idno>
                  <idno type="ARXIV">https://arxiv.org/a/romary_l_1</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/A-5114-2012</idno>
                  <idno type="IDREF">https://www.idref.fr/060702494</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0756-0508</idno>
                  <idno type="VIAF">https://viaf.org/viaf/282014122</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000388795444</idno>
                  <affiliation ref="#struct-482775"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Pierre</forename>
                    <surname>Mounier</surname>
                  </persName>
                  <email type="md5">4956155e6f8f80388e797ce0a2c7397f</email>
                  <email type="domain">numericat.net</email>
                  <idno type="idhal" notation="string">pierre-mounier</idno>
                  <idno type="idhal" notation="numeric">357</idno>
                  <idno type="halauthorid" notation="string">1405-357</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0691-6063</idno>
                  <idno type="IDREF">https://www.idref.fr/050447823</idno>
                  <affiliation ref="#struct-84824"/>
                  <affiliation ref="#struct-99539"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">88182</idno>
                <idno type="eissn">2416-5999</idno>
                <title level="j">Journal of Data Mining and Digital Humanities</title>
                <imprint>
                  <publisher>INRIA</publisher>
                  <biblScope unit="volume">2019</biblScope>
                  <date type="datePub">2020-06-15</date>
                </imprint>
              </monogr>
              <idno type="doi">10.46298/jdmdh.5081</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Digital Publishing Platforms</term>
                <term xml:lang="en">Monographs</term>
                <term xml:lang="en">Entity-Fishing</term>
                <term xml:lang="en">Named Entity Recognition and Disambiguation (NERD)</term>
                <term xml:lang="en">Open Access</term>
              </keywords>
              <classCode scheme="https://dl.acm.org/ccs" n="ACM2012.L.7.1"/>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</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>This paper addresses the integration of a Named Entity Recognition and Disambiguation (NERD) service within a group of open access (OA) publishing digital platforms and considers its potential impact on both research and scholarly publishing. The software powering this service, called entity-fishing, was initially developed by Inria in the context of the EU FP7 project CENDARI and provides automatic entity recognition and disambiguation using the Wikipedia and Wikidata data sets. The application is distributed with an open-source licence, and it has been deployed as a web service in DARIAH's infrastructure hosted by the French HumaNum. In the paper, we focus on the specific issues related to its integration on five OA platforms specialized in the publication of scholarly monographs in the social sciences and humanities (SSH), as part of the work carried out within the EU H2020 project HIRMEOS (High Integration of Research Monographs in the European Open Science infrastructure). In the first section, we give a brief overview of the current status and evolution of OA publications, considering specifically the challenges that OA monographs are encountering. In the second part, we show how the HIRMEOS project aims to face these challenges by optimizing five OA digital platforms for the publication of monographs from the SSH and ensuring their interoperability. In sections three and four we give a comprehensive description of the entity-fishing service, focusing on its concrete applications in real use cases together with some further possible ideas on how to exploit the annotations generated. We show that entity-fishing annotations can improve both research and publishing process. In the last chapter, we briefly present further possible application scenarios that could be made available through infrastructural projects.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-203762" status="VALID">
          <orgName>Göttingen State and University Library</orgName>
          <orgName type="acronym">SUB Göttingen</orgName>
          <desc>
            <address>
              <addrLine>Platz der Göttinger Sieben 1 37073 Göttingen</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">http://www.sub.uni-goettingen.de</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1065644" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-482775" status="VALID">
          <idno type="RNSR">201722248N</idno>
          <idno type="ROR">https://ror.org/05rnwy495</idno>
          <orgName>Automatic Language Modelling and ANAlysis &amp; Computational Humanities</orgName>
          <orgName type="acronym">ALMAnaCH</orgName>
          <date type="start">2017-01-01</date>
          <date type="end">2029-04-30</date>
          <desc>
            <address>
              <addrLine>48 Rue Barrault, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inria.fr/equipes/almanach</ref>
          </desc>
          <listRelation>
            <relation active="#struct-454310" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-84824" status="OLD">
          <idno type="IdRef">166217417</idno>
          <idno type="RNSR">201420921J</idno>
          <orgName>Centre pour l'édition électronique ouverte</orgName>
          <orgName type="acronym">CLEO</orgName>
          <date type="start">2009-01-01</date>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>OpenEdition (Cléo)c/o École centrale de Marseille – Technopôle de Château-Gombert38, rue Frédéric Joliot-Curie13 451 Marseille Cedex 13FRANCE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://cleo.cnrs.fr</ref>
          </desc>
          <listRelation>
            <relation name="USR2004" active="#struct-99539" type="direct"/>
            <relation name="USR2004" active="#struct-195507" type="direct"/>
            <relation name="USR2004" active="#struct-198056" type="direct"/>
            <relation name="UMS3287" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-99539" status="VALID">
          <idno type="IdRef">026374889</idno>
          <idno type="ROR">https://ror.org/02d9dg697</idno>
          <orgName>École des hautes études en sciences sociales</orgName>
          <orgName type="acronym">EHESS</orgName>
          <date type="start">1975-01-01</date>
          <desc>
            <address>
              <addrLine>54, boulevard Raspail 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ehess.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1065644" status="VALID">
          <idno type="ROR">https://ror.org/01y9bpm73</idno>
          <orgName>Georg-August-University of Goettingen = Georg-August-Universität Göttingen</orgName>
          <desc>
            <address>
              <addrLine>Wilhelmsplatz 1, 37073 Göttingen, Allemagne</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.uni-goettingen.de/en/1.html</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-454310" status="VALID">
          <idno type="IdRef">241614864</idno>
          <idno type="RNSR">196718247G</idno>
          <idno type="ROR">https://ror.org/05eyd5d35</idno>
          <orgName>Centre Inria de Paris</orgName>
          <date type="start">2016-03-10</date>
          <desc>
            <address>
              <addrLine>48 Rue Barrault, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/paris</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>
        <org type="institution" xml:id="struct-195507" status="VALID">
          <idno type="ROR">https://ror.org/00mfpxb84</idno>
          <orgName>Avignon Université</orgName>
          <orgName type="acronym">AU</orgName>
          <desc>
            <address>
              <addrLine>74 rue Louis Pasteur - 84 029 Avignon cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-avignon.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="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>