<?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-01122699</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="2026-05-20T01:55:15+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Big Data Methods for Computational Linguistics</title>
            <author role="aut">
              <persName>
                <forename type="first">Gerhard</forename>
                <surname>Weikum</surname>
              </persName>
              <idno type="halauthorid">505788-0</idno>
              <affiliation ref="#struct-54489"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Johannes</forename>
                <surname>Hoffart</surname>
              </persName>
              <idno type="halauthorid">556014-0</idno>
              <affiliation ref="#struct-54489"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ndapa</forename>
                <surname>Nakashole</surname>
              </persName>
              <idno type="halauthorid">893398-0</idno>
              <affiliation ref="#struct-54489"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marc</forename>
                <surname>Spaniol</surname>
              </persName>
              <email type="md5">d6ad903679ae407f427efbbbe9500f0c</email>
              <email type="domain">unicaen.fr</email>
              <idno type="idhal" notation="string">marc-spaniol</idno>
              <idno type="idhal" notation="numeric">753180</idno>
              <idno type="halauthorid" notation="string">24698-753180</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5094-4523</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.de/citations?user=SS1G5GIAAAAJ&amp;hl=de</idno>
              <affiliation ref="#struct-388300"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Fabian M.</forename>
                <surname>Suchanek</surname>
              </persName>
              <email type="md5">ea5bf13de9841dd0a0a6f9e33eb04e13</email>
              <email type="domain">suchanek.name</email>
              <idno type="idhal" notation="string">fabian-suchanek</idno>
              <idno type="idhal" notation="numeric">12540</idno>
              <idno type="halauthorid" notation="string">667953-12540</idno>
              <idno type="IDREF">https://www.idref.fr/203477707</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7189-2796</idno>
              <idno type="GOOGLE SCHOLAR">djtZhi8AAAAJ</idno>
              <affiliation ref="#struct-118082"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mohamed Amir</forename>
                <surname>Yosef</surname>
              </persName>
              <idno type="halauthorid">893261-0</idno>
              <affiliation ref="#struct-54489"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Marc</forename>
                <surname>Spaniol</surname>
              </persName>
              <email type="md5">d6ad903679ae407f427efbbbe9500f0c</email>
              <email type="domain">unicaen.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2015-03-04 13:55:47</date>
              <date type="whenWritten">2012</date>
              <date type="whenModified">2025-02-27 03:06:50</date>
              <date type="whenReleased">2015-03-04 13:55:47</date>
              <date type="whenProduced">2012</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="309379">
                <persName>
                  <forename>Marc</forename>
                  <surname>Spaniol</surname>
                </persName>
                <email type="md5">d6ad903679ae407f427efbbbe9500f0c</email>
                <email type="domain">unicaen.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01122699</idno>
            <idno type="halUri">https://hal.science/hal-01122699</idno>
            <idno type="halBibtex">weikum:hal-01122699</idno>
            <idno type="halRefHtml">&lt;i&gt;Bulletin of the Technical Committee on Data Engineering&lt;/i&gt;, 2012, pp.10</idno>
            <idno type="halRef">Bulletin of the Technical Committee on Data Engineering, 2012, pp.10</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="EC-PARIS">Ecole Centrale Paris</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-PSUD">Université Paris Sud - Paris XI</idno>
            <idno type="stamp" n="ENSI-CAEN">Ecole Nationale Supérieure d'Ingénieurs de Caen</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="GREYC">Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen (GREYC)</idno>
            <idno type="stamp" n="GREYC-HULTECH" corresp="GREYC">GREYC hultech</idno>
            <idno type="stamp" n="UMR8623">Laboratoire de Recherche en Informatique</idno>
            <idno type="stamp" n="COMUE-NORMANDIE">Normandie Université</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIV-PSUD-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris Sud pour Paris Saclay</idno>
            <idno type="stamp" n="ENSICAEN">École Nationale Supérieure d’Ingénieurs de Caen</idno>
            <idno type="stamp" n="UNICAEN">Université de Caen Normandie</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">Big Data Methods for Computational Linguistics</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Gerhard</forename>
                    <surname>Weikum</surname>
                  </persName>
                  <idno type="halauthorid">505788-0</idno>
                  <affiliation ref="#struct-54489"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Johannes</forename>
                    <surname>Hoffart</surname>
                  </persName>
                  <idno type="halauthorid">556014-0</idno>
                  <affiliation ref="#struct-54489"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ndapa</forename>
                    <surname>Nakashole</surname>
                  </persName>
                  <idno type="halauthorid">893398-0</idno>
                  <affiliation ref="#struct-54489"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marc</forename>
                    <surname>Spaniol</surname>
                  </persName>
                  <email type="md5">d6ad903679ae407f427efbbbe9500f0c</email>
                  <email type="domain">unicaen.fr</email>
                  <idno type="idhal" notation="string">marc-spaniol</idno>
                  <idno type="idhal" notation="numeric">753180</idno>
                  <idno type="halauthorid" notation="string">24698-753180</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5094-4523</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.de/citations?user=SS1G5GIAAAAJ&amp;hl=de</idno>
                  <affiliation ref="#struct-388300"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Fabian M.</forename>
                    <surname>Suchanek</surname>
                  </persName>
                  <email type="md5">ea5bf13de9841dd0a0a6f9e33eb04e13</email>
                  <email type="domain">suchanek.name</email>
                  <idno type="idhal" notation="string">fabian-suchanek</idno>
                  <idno type="idhal" notation="numeric">12540</idno>
                  <idno type="halauthorid" notation="string">667953-12540</idno>
                  <idno type="IDREF">https://www.idref.fr/203477707</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7189-2796</idno>
                  <idno type="GOOGLE SCHOLAR">djtZhi8AAAAJ</idno>
                  <affiliation ref="#struct-118082"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mohamed Amir</forename>
                    <surname>Yosef</surname>
                  </persName>
                  <idno type="halauthorid">893261-0</idno>
                  <affiliation ref="#struct-54489"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">124370</idno>
                <idno type="issn">1053-1238</idno>
                <title level="j">Bulletin of the Technical Committee on Data Engineering</title>
                <imprint>
                  <publisher>IEEE Computer Society</publisher>
                  <biblScope unit="pp">10</biblScope>
                  <date type="datePub">2012</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</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>Many tasks in computational linguistics traditionally rely on hand-crafted or curated resources like the-sauri or word-sense-annotated corpora. The availability of big data, from the Web and other sources,has changed this situation. Harnessing these assets requires scalable methods for data and text ana-lytics. This paper gives an overview on our recent work that utilizes big data methods for enhancingsemantics-centric tasks dealing with natural language texts. We demonstrate a virtuous cycle in harvest-ing knowledge from large data and text collections and leveraging this knowledge in order to improvethe annotation and interpretation of language in Web pages and social media. Specifically, we show howto build large dictionaries of names and paraphrases for entities and relations, and how these help todisambiguate entity mentions in texts.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-54489" status="VALID">
          <orgName>Max-Planck-Institut für Informatik</orgName>
          <orgName type="acronym">MPII</orgName>
          <desc>
            <address>
              <addrLine>Campus E-1 4, 66123 Saarbrücken, Germany</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">http://www.mpi-inf.mpg.de/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-5247" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-388300" status="VALID">
          <orgName>Equipe Hultech - Laboratoire GREYC - UMR6072</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-150" type="direct"/>
            <relation active="#struct-7127" type="indirect"/>
            <relation active="#struct-455934" type="indirect"/>
            <relation active="#struct-246955" type="indirect"/>
            <relation name="UMR6072" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-118082" status="OLD">
          <idno type="RNSR">201021232P</idno>
          <orgName>Distributed and heterogeneous data and knowledge</orgName>
          <orgName type="acronym">LEO</orgName>
          <desc>
            <address>
              <addrLine>Parc Club Orsay Université, 4 rue Jacques Monod - Bât G, 91893 Orsay Cedex France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/leo</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92966" type="direct"/>
            <relation active="#struct-118511" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation name="UMR8623" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-5247" status="VALID">
          <orgName>Max-Planck-Gesellschaft</orgName>
          <desc>
            <address>
              <addrLine>Jägerstrasse, 10-11, D-10117 Berlin</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.mpg.de/en</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-150" status="VALID">
          <idno type="IdRef">035827335</idno>
          <idno type="ISNI">0000 0000 9466 2590</idno>
          <idno type="RNSR">201722568L</idno>
          <idno type="ROR">https://ror.org/043749971</idno>
          <idno type="Wikidata">Q3117752</idno>
          <orgName>Groupe de Recherche en Informatique, Image et Instrumentation de Caen</orgName>
          <orgName type="acronym">GREYC</orgName>
          <date type="start">1995-01-01</date>
          <desc>
            <address>
              <addrLine>Boulevard du Maréchal Juin - 14050 CAEN Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.greyc.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-7127" type="direct"/>
            <relation active="#struct-455934" type="indirect"/>
            <relation active="#struct-246955" type="direct"/>
            <relation name="UMR6072" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-7127" status="VALID">
          <idno type="IdRef">026403064</idno>
          <idno type="ISNI">0000000121864076</idno>
          <idno type="ROR">https://ror.org/051kpcy16</idno>
          <orgName>Université de Caen Normandie</orgName>
          <orgName type="acronym">UNICAEN</orgName>
          <date type="start">1432-01-01</date>
          <desc>
            <address>
              <addrLine>Esplanade de la Paix - CS 14032 - 14032 CAEN Cedex 5</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.unicaen.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-455934" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-455934" status="VALID">
          <idno type="IdRef">190906332</idno>
          <idno type="ISNI">0000000417859671 </idno>
          <idno type="ROR">https://ror.org/01k40cz91</idno>
          <orgName>Normandie Université</orgName>
          <orgName type="acronym">NU</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Esplanade de la Paix - CS 14032 - 14032 Caen Cedex 5</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.normandie-univ.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-246955" status="VALID">
          <idno type="IdRef">190907991</idno>
          <idno type="ROR">https://ror.org/01fpqqe90</idno>
          <orgName>École Nationale Supérieure d'Ingénieurs de Caen</orgName>
          <orgName type="acronym">ENSICAEN</orgName>
          <desc>
            <address>
              <addrLine>6, Boulevard du Maréchal Juin CS 45053 14050 CAEN cedex 04</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ensicaen.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-455934" type="direct"/>
          </listRelation>
        </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-92966" status="OLD">
          <idno type="ROR">https://ror.org/028rypz17</idno>
          <orgName>Université Paris-Sud - Paris 11</orgName>
          <orgName type="acronym">UP11</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 300 - 91405 Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-psud.fr/</ref>
          </desc>
        </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>
        <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>