<?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-03180669</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="2026-05-11T06:36:08+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">An accessible and transparent pipeline for publishing historical egodocuments</title>
            <author role="aut">
              <persName>
                <forename type="first">Alix</forename>
                <surname>Chagué</surname>
              </persName>
              <email type="md5">8ec7bdaa00dc86c8bc2903b78d7d33d8</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">alix-chague</idno>
              <idno type="idhal" notation="numeric">170519</idno>
              <idno type="halauthorid" notation="string">41146-170519</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0136-4434</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=Pfs7W1wAAAAJ</idno>
              <affiliation ref="#struct-482775"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Floriane</forename>
                <surname>Chiffoleau</surname>
              </persName>
              <email type="md5">a3e1bdec978a845d27efaa249ab7c945</email>
              <email type="domain">hotmail.fr</email>
              <idno type="idhal" notation="string">floriane-chiffoleau</idno>
              <idno type="idhal" notation="numeric">744701</idno>
              <idno type="halauthorid" notation="string">39097-744701</idno>
              <idno type="IDREF">https://www.idref.fr/203093518</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4482-7897</idno>
              <idno type="VIAF">https://viaf.org/viaf/190150565736306252209</idno>
              <affiliation ref="#struct-482775"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Alix</forename>
                <surname>Chagué</surname>
              </persName>
              <email type="md5">8ec7bdaa00dc86c8bc2903b78d7d33d8</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder>DAHN</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-03-25 10:58:00</date>
              <date type="whenWritten">2021-03-17</date>
              <date type="whenModified">2025-09-12 17:04:02</date>
              <date type="whenReleased">2021-03-25 11:39:40</date>
              <date type="whenProduced">2021-03-17</date>
              <date type="whenEndEmbargoed">2021-03-25</date>
              <ref type="file" target="https://hal.science/hal-03180669v1/document">
                <date notBefore="2021-03-25"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03180669v1/file/achague_fchiffoleau_dahn_wpip2021.pdf" id="file-3180669-2790338">
                <date notBefore="2021-03-25"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="634060">
                <persName>
                  <forename>Alix</forename>
                  <surname>Chagué</surname>
                </persName>
                <email type="md5">8ec7bdaa00dc86c8bc2903b78d7d33d8</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03180669</idno>
            <idno type="halUri">https://hal.science/hal-03180669</idno>
            <idno type="halBibtex">chague:hal-03180669</idno>
            <idno type="halRefHtml">2021</idno>
            <idno type="halRef">2021</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-3180669-2790338"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SHS">Sciences de l'Homme et de la Société</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-ROCQ">INRIA Paris - Rocquencourt</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="INTERDISCIPLINARITES">Interdisciplinarités</idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">An accessible and transparent pipeline for publishing historical egodocuments</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Alix</forename>
                    <surname>Chagué</surname>
                  </persName>
                  <email type="md5">8ec7bdaa00dc86c8bc2903b78d7d33d8</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">alix-chague</idno>
                  <idno type="idhal" notation="numeric">170519</idno>
                  <idno type="halauthorid" notation="string">41146-170519</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0136-4434</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=Pfs7W1wAAAAJ</idno>
                  <affiliation ref="#struct-482775"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Floriane</forename>
                    <surname>Chiffoleau</surname>
                  </persName>
                  <email type="md5">a3e1bdec978a845d27efaa249ab7c945</email>
                  <email type="domain">hotmail.fr</email>
                  <idno type="idhal" notation="string">floriane-chiffoleau</idno>
                  <idno type="idhal" notation="numeric">744701</idno>
                  <idno type="halauthorid" notation="string">39097-744701</idno>
                  <idno type="IDREF">https://www.idref.fr/203093518</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4482-7897</idno>
                  <idno type="VIAF">https://viaf.org/viaf/190150565736306252209</idno>
                  <affiliation ref="#struct-482775"/>
                </author>
              </analytic>
              <monogr>
                <imprint/>
              </monogr>
              <ref target="https://hal.archives-ouvertes.fr/hal-03173038" type="seeAlso"/>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Optical Character Recognition</term>
                <term xml:lang="en">Egodocument</term>
                <term xml:lang="en">Digital editions</term>
                <term xml:lang="en">FAIR principles</term>
                <term xml:lang="en">TEI encoding</term>
                <term xml:lang="en">Workflow</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</classCode>
              <classCode scheme="halDomain" n="shs">Humanities and Social Sciences</classCode>
              <classCode scheme="halDomain" n="shs.litt">Humanities and Social Sciences/Literature</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>The automatization of the processing of documents oriented towards online publication and exploration by the humanities increases the rapidity of treatments like the transcription, but they should also be an opportunity to make the experimentation and the resulting corpora sustainable and reusable. The DAHN project (Dispositif de soutien à l’Archivistique et aux Humanités Numériques) relies on a joint interdisciplinary collaboration between Inria, the EHESS and the University of Le Mans. By taking theexample of egodocuments, the project aims to create a ready-to-use digital and scientific publishing pipeline going from the material archive to an online publication.In this presentation, we introduce our method and guidelines for the processing of non-digital-native textual documents using open-source and easily hackable tools that guarantee visibility across an accessible pipeline, thus challenging the notions of a black box or scattered tools which tend to be hard to maintain in the long run.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <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-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>
      </listOrg>
    </back>
  </text>
</TEI>