<?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-04110765</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="2026-05-23T02:33:09+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A Data-driven Approach to Named Entity Recognition for Early Modern French</title>
            <author role="aut">
              <persName>
                <forename type="first">Pedro</forename>
                <surname>Ortiz Suarez</surname>
              </persName>
              <email type="md5">e97084bdef43fdef2600ec7bed0d0273</email>
              <email type="domain">potizs.eu</email>
              <idno type="idhal" notation="string">pedro-ortiz-suarez</idno>
              <idno type="idhal" notation="numeric">178412</idno>
              <idno type="halauthorid" notation="string">55590-178412</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0343-8852</idno>
              <idno type="ARXIV">https://arxiv.org/a/ortizsuarez_p_1</idno>
              <idno type="IDREF">https://www.idref.fr/264210743</idno>
              <idno type="VIAF">https://viaf.org/viaf/59166596794217591423</idno>
              <affiliation ref="#struct-1143778"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Simon</forename>
                <surname>Gabay</surname>
              </persName>
              <email type="md5">a6570d84251469a7c59211b176a990cf</email>
              <email type="domain">unige.ch</email>
              <idno type="idhal" notation="string">simon-gabay</idno>
              <idno type="idhal" notation="numeric">21216</idno>
              <idno type="halauthorid" notation="string">40571-21216</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-9094-4475</idno>
              <idno type="VIAF">https://viaf.org/viaf/305833240</idno>
              <idno type="ISNI">http://isni.org/isni/0000000419576448</idno>
              <idno type="VIAF">https://viaf.org/viaf/816165264164810190032</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=7MymdvIAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/261700286</idno>
              <affiliation ref="#struct-154620"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Simon</forename>
                <surname>Gabay</surname>
              </persName>
              <email type="md5">a6570d84251469a7c59211b176a990cf</email>
              <email type="domain">unige.ch</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-05-30 19:59:55</date>
              <date type="whenModified">2024-12-18 22:58:02</date>
              <date type="whenReleased">2023-06-22 13:45:59</date>
              <date type="whenProduced">2022-10-12</date>
              <date type="whenEndEmbargoed">2023-05-30</date>
              <ref type="file" target="https://hal.science/hal-04110765v1/document">
                <date notBefore="2023-05-30"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04110765v1/file/2022.coling-1.327.pdf" id="file-4110765-3579050">
                <date notBefore="2023-05-30"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="503709">
                <persName>
                  <forename>Simon</forename>
                  <surname>Gabay</surname>
                </persName>
                <email type="md5">a6570d84251469a7c59211b176a990cf</email>
                <email type="domain">unige.ch</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04110765</idno>
            <idno type="halUri">https://hal.science/hal-04110765</idno>
            <idno type="halBibtex">ortizsuarez:hal-04110765</idno>
            <idno type="halRefHtml">&lt;i&gt;Proceedings of the 29th International Conference on Computational Linguistics&lt;/i&gt;, International Committee on Computational Linguistics, Oct 2022, Gyeongju, South Korea. pp.3722-3730</idno>
            <idno type="halRef">Proceedings of the 29th International Conference on Computational Linguistics, International Committee on Computational Linguistics, Oct 2022, Gyeongju, South Korea. pp.3722-3730</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4110765-3579050"/></licence>
            </availability>
          </publicationStmt>
          <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">A Data-driven Approach to Named Entity Recognition for Early Modern French</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Pedro</forename>
                    <surname>Ortiz Suarez</surname>
                  </persName>
                  <email type="md5">e97084bdef43fdef2600ec7bed0d0273</email>
                  <email type="domain">potizs.eu</email>
                  <idno type="idhal" notation="string">pedro-ortiz-suarez</idno>
                  <idno type="idhal" notation="numeric">178412</idno>
                  <idno type="halauthorid" notation="string">55590-178412</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0343-8852</idno>
                  <idno type="ARXIV">https://arxiv.org/a/ortizsuarez_p_1</idno>
                  <idno type="IDREF">https://www.idref.fr/264210743</idno>
                  <idno type="VIAF">https://viaf.org/viaf/59166596794217591423</idno>
                  <affiliation ref="#struct-1143778"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Simon</forename>
                    <surname>Gabay</surname>
                  </persName>
                  <email type="md5">a6570d84251469a7c59211b176a990cf</email>
                  <email type="domain">unige.ch</email>
                  <idno type="idhal" notation="string">simon-gabay</idno>
                  <idno type="idhal" notation="numeric">21216</idno>
                  <idno type="halauthorid" notation="string">40571-21216</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-9094-4475</idno>
                  <idno type="VIAF">https://viaf.org/viaf/305833240</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000419576448</idno>
                  <idno type="VIAF">https://viaf.org/viaf/816165264164810190032</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=7MymdvIAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/261700286</idno>
                  <affiliation ref="#struct-154620"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Proceedings of the 29th International Conference on Computational Linguistics</title>
                  <date type="start">2022-10-12</date>
                  <date type="end">2022-10-17</date>
                  <settlement>Gyeongju</settlement>
                  <country key="KR">South Korea</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>International Committee on Computational Linguistics</name>
                </respStmt>
                <imprint>
                  <biblScope unit="issue">2022.coling-1.327</biblScope>
                  <biblScope unit="pp">3722–3730</biblScope>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Named entity recognition</term>
                <term xml:lang="en">Diachronic linguistics</term>
                <term xml:lang="en">Named entity recognition</term>
                <term xml:lang="fr">Linguistique diachronique</term>
                <term xml:lang="fr">Reconnaissance d'entités nommées</term>
                <term xml:lang="fr">Linguistique diachronique</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</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>Named entity recognition has become an increasingly useful tool for digital humanities research, specially when it comes to historical texts. However, historical texts pose a wide range of challenges to both named entity recognition and natural language processing in general that are still difficult to address even with modern neural methods. In this article we focus in named entity recognition for historical French, and in particular for Early Modern French (16th-18 th c.), i.e. Ancien Régime French. However, instead of developing a specialised architecture to tackle the particularities of this state of language, we opt for a data-driven approach by developing a new corpus with fine-grained entity annotation, covering three centuries of literature corresponding to the early modern period; we try to annotate as much data as possible producing a corpus that is many times bigger than the most popular NER evaluation corpora for both Contemporary English and French. We then fine-tune existing state-of-the-art architectures for Early Modern and Contemporary French, obtaining results that are on par with those of the current state-of-the-art NER systems for Contemporary English. Both the corpus and the fine-tuned models are released.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1143778" status="VALID">
          <orgName>Data and Web Science Group [Mannheim Univ]</orgName>
          <orgName type="acronym">DWS</orgName>
          <desc>
            <address>
              <addrLine>University of Mannheim | School of Business Informatics and Mathematics, 68159 Mannheim</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.uni-mannheim.de/dws/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-254729" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-154620" status="VALID">
          <idno type="ROR">https://ror.org/01swzsf04</idno>
          <orgName>Université de Genève = University of Geneva</orgName>
          <orgName type="acronym">UNIGE</orgName>
          <date type="start">1559-01-01</date>
          <desc>
            <address>
              <addrLine>24 rue du Général-Dufour CH - 1211 Genève 4Suisse</addrLine>
              <country key="CH"/>
            </address>
            <ref type="url">http://www.unige.ch/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-254729" status="VALID">
          <idno type="ROR">https://ror.org/031bsb921</idno>
          <orgName>University of Mannheim = Universität Mannheim</orgName>
          <desc>
            <address>
              <addrLine>Schloss, 68131 Mannheim</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.uni-mannheim.de/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>