<?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-01490004</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="2026-05-12T12:00:23+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Tree-Structured Named Entity Recognition on OCR Data: Analysis, Processing and Results</title>
            <author role="aut">
              <persName>
                <forename type="first">Marco</forename>
                <surname>Dinarelli</surname>
              </persName>
              <email type="md5">d3844322af1769c4d5851ee1846994a9</email>
              <email type="domain">univ-grenoble-alpes.fr</email>
              <idno type="idhal" notation="string">marco-dinarelli</idno>
              <idno type="idhal" notation="numeric">12699</idno>
              <idno type="halauthorid" notation="string">34131-12699</idno>
              <idno type="IDREF">https://www.idref.fr/22461939X</idno>
              <idno type="ORCID">https://orcid.org/0009-0005-4788-4899</idno>
              <affiliation ref="#struct-59704"/>
              <affiliation ref="#struct-303171"/>
              <affiliation ref="#struct-564132"/>
              <affiliation ref="#struct-104851"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sophie</forename>
                <surname>Rosset</surname>
              </persName>
              <email type="md5">dbb4013fd09f2b07c31e3a8e3878f7bc</email>
              <email type="domain">limsi.fr</email>
              <idno type="idhal" notation="string">sophie-rosset</idno>
              <idno type="idhal" notation="numeric">14913</idno>
              <idno type="halauthorid" notation="string">11264-14913</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-6865-4989</idno>
              <idno type="IDREF">https://www.idref.fr/137157835</idno>
              <idno type="ISNI">http://isni.org/isni/0000000357034976</idno>
              <idno type="VIAF">https://viaf.org/viaf/193001246</idno>
              <affiliation ref="#struct-247329"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Marco</forename>
                <surname>Dinarelli</surname>
              </persName>
              <email type="md5">d3844322af1769c4d5851ee1846994a9</email>
              <email type="domain">univ-grenoble-alpes.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2017-03-15 15:24:22</date>
              <date type="whenModified">2026-02-19 15:59:21</date>
              <date type="whenReleased">2017-03-16 11:37:03</date>
              <date type="whenProduced">2012-05-21</date>
              <date type="whenEndEmbargoed">2017-03-14</date>
              <ref type="file" target="https://hal.science/hal-01490004v1/document">
                <date notBefore="2017-03-14"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-01490004v1/file/LREC2012_OCR-NER.pdf" id="file-1490004-1554847">
                <date notBefore="2017-03-14"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="391229">
                <persName>
                  <forename>Marco</forename>
                  <surname>Dinarelli</surname>
                </persName>
                <email type="md5">d3844322af1769c4d5851ee1846994a9</email>
                <email type="domain">univ-grenoble-alpes.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01490004</idno>
            <idno type="halUri">https://hal.science/hal-01490004</idno>
            <idno type="halBibtex">dinarelli:hal-01490004</idno>
            <idno type="halRefHtml">&lt;i&gt;LREC 2012 - 8th International Conference on Language Resources and Evaluation&lt;/i&gt;, May 2012, Istanbul, Turkey</idno>
            <idno type="halRef">LREC 2012 - 8th International Conference on Language Resources and Evaluation, May 2012, Istanbul, Turkey</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1490004-1554847"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="ENS-PARIS">Ecole Normale Supérieure de Paris</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-PARIS3">Université Sorbonne Nouvelle</idno>
            <idno type="stamp" n="UNIV-PSUD">Université Paris Sud - Paris XI</idno>
            <idno type="stamp" n="LATTICE" corresp="ENS-PARIS">Langues, textes, traitement informatique, cognition</idno>
            <idno type="stamp" n="LIMSI">Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur</idno>
            <idno type="stamp" n="PSL">Université Paris sciences et lettres</idno>
            <idno type="stamp" n="UNIV-PSUD-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris Sud pour Paris Saclay</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SU-INF-2018" corresp="SORBONNE-UNIVERSITE">SORBONNE université &lt;2018</idno>
            <idno type="stamp" n="ENS-PSL" corresp="PSL">École normale supérieure - PSL</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="LISN">Laboratoire Interdisciplinaire des Sciences du Numérique</idno>
            <idno type="stamp" n="GS-SPORT-HUMAN-MOVEMENT">Graduate School Sport, Mouvement, Facteurs Humains</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Tree-Structured Named Entity Recognition on OCR Data: Analysis, Processing and Results</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Marco</forename>
                    <surname>Dinarelli</surname>
                  </persName>
                  <email type="md5">d3844322af1769c4d5851ee1846994a9</email>
                  <email type="domain">univ-grenoble-alpes.fr</email>
                  <idno type="idhal" notation="string">marco-dinarelli</idno>
                  <idno type="idhal" notation="numeric">12699</idno>
                  <idno type="halauthorid" notation="string">34131-12699</idno>
                  <idno type="IDREF">https://www.idref.fr/22461939X</idno>
                  <idno type="ORCID">https://orcid.org/0009-0005-4788-4899</idno>
                  <affiliation ref="#struct-59704"/>
                  <affiliation ref="#struct-303171"/>
                  <affiliation ref="#struct-564132"/>
                  <affiliation ref="#struct-104851"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sophie</forename>
                    <surname>Rosset</surname>
                  </persName>
                  <email type="md5">dbb4013fd09f2b07c31e3a8e3878f7bc</email>
                  <email type="domain">limsi.fr</email>
                  <idno type="idhal" notation="string">sophie-rosset</idno>
                  <idno type="idhal" notation="numeric">14913</idno>
                  <idno type="halauthorid" notation="string">11264-14913</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-6865-4989</idno>
                  <idno type="IDREF">https://www.idref.fr/137157835</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000357034976</idno>
                  <idno type="VIAF">https://viaf.org/viaf/193001246</idno>
                  <affiliation ref="#struct-247329"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">LREC 2012 proceedings</title>
                <meeting>
                  <title>LREC 2012 - 8th International Conference on Language Resources and Evaluation</title>
                  <date type="start">2012-05-21</date>
                  <date type="end">2012-05-27</date>
                  <settlement>Istanbul</settlement>
                  <country key="TR">Turkey</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">automatic OCR correction</term>
                <term xml:lang="en">old newspapers</term>
                <term xml:lang="en">Named Entity detection</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>In this paper we deal with named entity detection on data acquired via OCR process on documents dating from 1890. The resulting corpus is very noisy. We perform an analysis to find possible strategies to overcome errors introduced by the OCR process. We propose a preprocessing procedure in three steps to clean data and correct, at least in part, OCR mistakes. The task is made even harder by the complex tree-structure of named entities annotated on data, we solve this problem however by adopting an effective named entity detection system we proposed in previous work. We evaluate our procedure for preprocessing OCR-ized data in two ways: in terms of perplexity and OOV rate of a language model on development and evaluation data, and in terms of the performance of the named entity detection system on the preprocessed data. The preprocessing procedure results to be effective, allowing to improve by a large margin the system we proposed for the official evaluation campaign on Old Press, and allowing to outperform also the best performing system of the evaluation campaign.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-59704" status="VALID">
          <idno type="IdRef">031738419</idno>
          <idno type="ISNI">0000000123532622</idno>
          <idno type="ROR">https://ror.org/05a0dhs15</idno>
          <orgName>École normale supérieure - Paris</orgName>
          <orgName type="acronym">ENS-PSL</orgName>
          <date type="start">1985-07-24</date>
          <desc>
            <address>
              <addrLine>45, Rue d'Ulm - 75230 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ens.psl.eu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-564132" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-303171" status="VALID">
          <idno type="IdRef">19077990X</idno>
          <idno type="ROR">https://ror.org/001z21q04</idno>
          <orgName>Université Sorbonne Paris Cité</orgName>
          <orgName type="acronym">USPC</orgName>
          <date type="start">2010-01-01</date>
          <desc>
            <address>
              <addrLine>Université Sorbonne Paris Cité | 100-104, avenue de France | 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-paris-cite.fr/fr</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-564132" status="VALID">
          <idno type="IdRef">241597595</idno>
          <idno type="ISNI">0000 0004 1784 3645</idno>
          <idno type="ROR">https://ror.org/013cjyk83</idno>
          <orgName>Université Paris Sciences et Lettres</orgName>
          <orgName type="acronym">PSL</orgName>
          <desc>
            <address>
              <addrLine>60 rue Mazarine 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.psl.eu/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-104851" status="VALID">
          <idno type="IdRef">161419992</idno>
          <idno type="RNSR">200012753S</idno>
          <idno type="ROR">https://ror.org/03ms1y683</idno>
          <orgName>Lattice - Langues, Textes, Traitements informatiques, Cognition - UMR 8094</orgName>
          <orgName type="acronym">Lattice</orgName>
          <date type="start">2000-01-01</date>
          <desc>
            <address>
              <addrLine>Lattice - ENS 1, rue Maurice Arnoux 92120 Montrouge</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lattice.cnrs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-52995" type="direct"/>
            <relation active="#struct-303171" type="direct"/>
            <relation name="UMR8094" active="#struct-441569" type="direct"/>
            <relation active="#struct-564132" type="direct"/>
            <relation active="#struct-1072648" type="direct"/>
            <relation active="#struct-59704" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-247329" status="OLD">
          <orgName>Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur</orgName>
          <orgName type="acronym">LIMSI</orgName>
          <date type="start">1962-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Université Paris-Sud Bât. 507 - Rue du Belvédère -91405 ORSAY CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.limsi.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92966" type="direct"/>
            <relation active="#struct-408837" type="direct"/>
            <relation active="#struct-413221" type="indirect"/>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UPR3251" active="#struct-441569" type="direct"/>
            <relation active="#struct-562112" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-52995" status="VALID">
          <idno type="IdRef">027361837</idno>
          <idno type="ISNI">0000 0004 1937 060X </idno>
          <idno type="ROR">https://ror.org/03z6jp965</idno>
          <orgName>Université Sorbonne Nouvelle - Paris 3</orgName>
          <date type="start">1970-01-01</date>
          <desc>
            <address>
              <addrLine>17, rue de la Sorbonne - 75231 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-paris3.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="regrouplaboratory" xml:id="struct-1072648" status="VALID">
          <orgName>Département Littératures et langage - ENS-PSL</orgName>
          <orgName type="acronym">LILA</orgName>
          <desc>
            <address>
              <addrLine>ENS, 45, rue d'Ulm75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://litteratures.ens.psl.eu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-59704" type="direct"/>
            <relation active="#struct-564132" type="indirect"/>
          </listRelation>
        </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="regrouplaboratory" xml:id="struct-408837" status="VALID">
          <orgName>Sorbonne Université - UFR d'Ingénierie</orgName>
          <orgName type="acronym">UFR 919</orgName>
          <desc>
            <address>
              <addrLine>SORBONNE UNIVERSITEFACULTE DES SCIENCES ET INGENIERIEUFR D'INGENIERIETour 55/65 - 2e étage4 place Jussieu75252 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ingenierie.sorbonne-universite.fr/fr/index.html</ref>
          </desc>
          <listRelation>
            <relation active="#struct-413221" type="direct"/>
          </listRelation>
        </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-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="institution" xml:id="struct-562112" status="OLD">
          <orgName>Université Paris Saclay (COmUE)</orgName>
          <desc>
            <address>
              <addrLine>Espace Technologique, Bât. Discovery - RD 128 - 2è ététage, 91190 Saint-Aubin</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/fr</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>