<?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-05111169</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="2026-05-04T08:59:39+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Token and Span Classification for Entity Recognition in French Historical Encyclopedias</title>
            <author role="aut">
              <persName>
                <forename type="first">Ludovic</forename>
                <surname>Moncla</surname>
              </persName>
              <email type="md5">3268d878f053957bc6789def8a64ab2a</email>
              <email type="domain">liris.cnrs.fr</email>
              <ptr type="url" target="https://ludovicmoncla.github.io"/>
              <idno type="idhal" notation="string">ludovic-moncla</idno>
              <idno type="idhal" notation="numeric">172</idno>
              <idno type="halauthorid" notation="string">18672-172</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1590-9546</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=KlJc_7kAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/190370491</idno>
              <idno type="ARXIV">https://arxiv.org/a/moncla_l_1</idno>
              <affiliation ref="#struct-413086"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hédi</forename>
                <surname>Zeghidi</surname>
              </persName>
              <idno type="halauthorid">2980848-0</idno>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Ludovic</forename>
                <surname>Moncla</surname>
              </persName>
              <email type="md5">3268d878f053957bc6789def8a64ab2a</email>
              <email type="domain">liris.cnrs.fr</email>
            </editor>
            <funder ref="#projanr-49753"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-06-13 12:03:14</date>
              <date type="whenWritten">2025-06-03</date>
              <date type="whenModified">2025-09-03 09:57:37</date>
              <date type="whenReleased">2025-06-13 13:26:09</date>
              <date type="whenProduced">2025-06-03</date>
              <date type="whenEndEmbargoed">2025-06-13</date>
              <ref type="file" target="https://hal.science/hal-05111169v1/document">
                <date notBefore="2025-06-13"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05111169v1/file/2506.02872v1.pdf" id="file-5111169-4420281">
                <date notBefore="2025-06-13"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2506.02872"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="201801">
                <persName>
                  <forename>Ludovic</forename>
                  <surname>Moncla</surname>
                </persName>
                <email type="md5">3268d878f053957bc6789def8a64ab2a</email>
                <email type="domain">liris.cnrs.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05111169</idno>
            <idno type="halUri">https://hal.science/hal-05111169</idno>
            <idno type="halBibtex">moncla:hal-05111169</idno>
            <idno type="halRefHtml">2025</idno>
            <idno type="halRef">2025</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5111169-4420281"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-LYON1">Université Claude Bernard - Lyon I</idno>
            <idno type="stamp" n="UNIV-LYON2">Université Lumière Lyon 2</idno>
            <idno type="stamp" n="INSA-LYON">Institut National des Sciences Appliquées de Lyon</idno>
            <idno type="stamp" n="EC-LYON">Ecole Centrale de Lyon</idno>
            <idno type="stamp" n="LIRIS" corresp="UNIV-LYON1">Laboratoire d'InfoRmatique en Image et Systèmes d'information</idno>
            <idno type="stamp" n="LYON2">Université Lyon2</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ASLAN-GEODE">Encyclopedic Geographical Discourse: Writing about Geography in France from the Enlightenment to the Age of Wikipedia</idno>
            <idno type="stamp" n="HAL-LYON-2-NOUVELLE-VERSION">Nouvelle version portail </idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Token and Span Classification for Entity Recognition in French Historical Encyclopedias</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Ludovic</forename>
                    <surname>Moncla</surname>
                  </persName>
                  <email type="md5">3268d878f053957bc6789def8a64ab2a</email>
                  <email type="domain">liris.cnrs.fr</email>
                  <ptr type="url" target="https://ludovicmoncla.github.io"/>
                  <idno type="idhal" notation="string">ludovic-moncla</idno>
                  <idno type="idhal" notation="numeric">172</idno>
                  <idno type="halauthorid" notation="string">18672-172</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1590-9546</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=KlJc_7kAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/190370491</idno>
                  <idno type="ARXIV">https://arxiv.org/a/moncla_l_1</idno>
                  <affiliation ref="#struct-413086"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hédi</forename>
                    <surname>Zeghidi</surname>
                  </persName>
                  <idno type="halauthorid">2980848-0</idno>
                </author>
              </analytic>
              <monogr>
                <imprint>
                  <date type="datePub">2025-06-03</date>
                </imprint>
              </monogr>
              <idno type="arxiv">2506.02872</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Computation and Language (cs.CL)</term>
                <term xml:lang="en">Information Retrieval (cs.IR)</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Named Entity Recognition (NER) in historical texts presents unique challenges due to non-standardized language, archaic orthography, and nested or overlapping entities. This study benchmarks a diverse set of NER approaches, ranging from classical Conditional Random Fields (CRFs) and spaCy-based models to transformer-based architectures such as CamemBERT and sequence-labeling models like Flair. Experiments are conducted on the GeoEDdA dataset, a richly annotated corpus derived from 18th-century French encyclopedias. We propose framing NER as both tokenlevel and span-level classification to accommodate complex nested entity structures typical of historical documents. Additionally, we evaluate the emerging potential of fewshot prompting with generative language models for low-resource scenarios. Our results demonstrate that while transformer-based models achieve state-of-the-art performance, especially on nested entities, generative models offer promising alternatives when labeled data are scarce. The study highlights ongoing challenges in historical NER and suggests avenues for hybrid approaches combining symbolic and neural methods to better capture the intricacies of early modern French text.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-413086" status="VALID">
          <orgName>Data Mining and Machine Learning</orgName>
          <orgName type="acronym">DM2L</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-2003" type="direct"/>
            <relation active="#struct-33804" type="indirect"/>
            <relation active="#struct-126765" type="indirect"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="indirect"/>
            <relation active="#struct-219748" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2003" status="VALID">
          <idno type="IdRef">149705271</idno>
          <idno type="ISNI">0000000122577669</idno>
          <idno type="RNSR">200511875R</idno>
          <idno type="ROR">https://ror.org/04dv4he91</idno>
          <orgName>Laboratoire d'InfoRmatique en Image et Systèmes d'information</orgName>
          <orgName type="acronym">LIRIS</orgName>
          <date type="start">2003-01-01</date>
          <desc>
            <address>
              <addrLine>Bâtiment Blaise Pascal - 20, avenue Albert Einstein - 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://liris.cnrs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-33804" type="direct"/>
            <relation active="#struct-126765" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="direct"/>
            <relation active="#struct-219748" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-33804" status="VALID">
          <idno type="IdRef">02640334X</idno>
          <idno type="ISNI">0000 0001 2188 0906</idno>
          <idno type="ROR">https://ror.org/03rth4p18</idno>
          <idno type="Wikidata">Q4041</idno>
          <orgName>Université Lumière - Lyon 2</orgName>
          <orgName type="acronym">UL2</orgName>
          <desc>
            <address>
              <addrLine>86, rue Pasteur - 69007 Lyon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon2.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-126765" status="VALID">
          <idno type="ROR">https://ror.org/05s6rge65</idno>
          <orgName>École Centrale de Lyon</orgName>
          <orgName type="acronym">ECL</orgName>
          <desc>
            <address>
              <addrLine>36 avenue Guy de Collongue - 69134 Ecully cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ec-lyon.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301088" status="VALID">
          <idno type="ROR">https://ror.org/01rk35k63</idno>
          <orgName>Université de Lyon</orgName>
          <desc>
            <address>
              <addrLine>92 rue Pasteur - CS 30122, 69361 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-lyon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-194495" status="VALID">
          <idno type="IdRef">026402823</idno>
          <idno type="ISNI">0000000121686185</idno>
          <idno type="ROR">https://ror.org/029brtt94</idno>
          <orgName>Université Claude Bernard Lyon 1</orgName>
          <orgName type="acronym">UCBL</orgName>
          <desc>
            <address>
              <addrLine>43, boulevard du 11 novembre 1918, 69622 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-219748" status="VALID">
          <idno type="IdRef">052444724</idno>
          <idno type="ISNI">0000 0001 2292 0228</idno>
          <orgName>Institut National des Sciences Appliquées de Lyon</orgName>
          <orgName type="acronym">INSA Lyon</orgName>
          <date type="start">1957-03-18</date>
          <desc>
            <address>
              <addrLine>20 Avenue Albert Einstein, 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-lyon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
            <relation active="#struct-301232" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </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>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-49753" status="VALID">
          <idno type="anr">ANR-10-LABX-0081</idno>
          <orgName>ASLAN</orgName>
          <desc>Advanced Studies on Language Complexity</desc>
          <date type="start">2010</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>