<?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-02512217v2</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="2026-05-13T18:36:52+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Automatic Identification of Types of Alterations in Historical Manuscripts</title>
            <author role="aut">
              <persName>
                <forename type="first">David</forename>
                <surname>Lassner</surname>
              </persName>
              <idno type="halauthorid">1809095-0</idno>
              <affiliation ref="#struct-86624"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Anne</forename>
                <surname>Baillot</surname>
              </persName>
              <email type="md5">e81d4b35751d2e3f110a9b12fed0fbf7</email>
              <email type="domain">univ-lemans.fr</email>
              <idno type="idhal" notation="string">annebaillot</idno>
              <idno type="idhal" notation="numeric">3610</idno>
              <idno type="halauthorid" notation="string">24997-3610</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4593-059X</idno>
              <idno type="VIAF">https://viaf.org/viaf/39592455</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=YbT-S-EAAAAJ&amp;hl=en&amp;oi=ao</idno>
              <idno type="IDREF">https://www.idref.fr/073633828</idno>
              <affiliation ref="#struct-182700"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sergej</forename>
                <surname>Dogadov</surname>
              </persName>
              <idno type="halauthorid">1809096-0</idno>
              <affiliation ref="#struct-86624"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Klaus-Robert</forename>
                <surname>Müller</surname>
              </persName>
              <idno type="halauthorid">1809097-0</idno>
              <affiliation ref="#struct-86624"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Shinichi</forename>
                <surname>Nakajima</surname>
              </persName>
              <idno type="halauthorid">1809098-0</idno>
              <affiliation ref="#struct-86624"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Anne</forename>
                <surname>Baillot</surname>
              </persName>
              <email type="md5">30792badbd7ee1c5bb02c8ee17a5d9bf</email>
              <email type="domain">dariah.eu</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2020-03-19 14:40:54</date>
            </edition>
            <edition n="v2" type="current">
              <date type="whenSubmitted">2020-03-20 12:06:11</date>
              <date type="whenWritten">2020-03-19</date>
              <date type="whenModified">2024-05-24 19:48:04</date>
              <date type="whenReleased">2020-03-23 09:10:35</date>
              <date type="whenProduced">2020-03-19</date>
              <date type="whenEndEmbargoed">2020-03-20</date>
              <ref type="file" target="https://hal.science/hal-02512217v2/document">
                <date notBefore="2020-03-20"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02512217v2/file/20200320_dhq_no_copyright_images.pdf" id="file-2513147-2388491">
                <date notBefore="2020-03-20"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2003.09136"/>
            </edition>
            <edition n="v3">
              <date type="whenSubmitted">2020-11-03 15:12:53</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="170671">
                <persName>
                  <forename>Anne</forename>
                  <surname>Baillot</surname>
                </persName>
                <email type="md5">30792badbd7ee1c5bb02c8ee17a5d9bf</email>
                <email type="domain">dariah.eu</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02512217</idno>
            <idno type="halUri">https://hal.science/hal-02512217</idno>
            <idno type="halBibtex">lassner:hal-02512217</idno>
            <idno type="halRefHtml">2020</idno>
            <idno type="halRef">2020</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-2513147-2388491"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt/>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Automatic Identification of Types of Alterations in Historical Manuscripts</title>
                <author role="aut">
                  <persName>
                    <forename type="first">David</forename>
                    <surname>Lassner</surname>
                  </persName>
                  <idno type="halauthorid">1809095-0</idno>
                  <affiliation ref="#struct-86624"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Anne</forename>
                    <surname>Baillot</surname>
                  </persName>
                  <email type="md5">e81d4b35751d2e3f110a9b12fed0fbf7</email>
                  <email type="domain">univ-lemans.fr</email>
                  <idno type="idhal" notation="string">annebaillot</idno>
                  <idno type="idhal" notation="numeric">3610</idno>
                  <idno type="halauthorid" notation="string">24997-3610</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4593-059X</idno>
                  <idno type="VIAF">https://viaf.org/viaf/39592455</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=YbT-S-EAAAAJ&amp;hl=en&amp;oi=ao</idno>
                  <idno type="IDREF">https://www.idref.fr/073633828</idno>
                  <affiliation ref="#struct-182700"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sergej</forename>
                    <surname>Dogadov</surname>
                  </persName>
                  <idno type="halauthorid">1809096-0</idno>
                  <affiliation ref="#struct-86624"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Klaus-Robert</forename>
                    <surname>Müller</surname>
                  </persName>
                  <idno type="halauthorid">1809097-0</idno>
                  <affiliation ref="#struct-86624"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Shinichi</forename>
                    <surname>Nakajima</surname>
                  </persName>
                  <idno type="halauthorid">1809098-0</idno>
                  <affiliation ref="#struct-86624"/>
                </author>
              </analytic>
              <monogr>
                <imprint/>
              </monogr>
              <idno type="arxiv">2003.09136</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Digital Editions</term>
                <term xml:lang="en">Machin Learning</term>
                <term xml:lang="en">Latent Dirichlet Allocation</term>
                <term xml:lang="en">Topic Modeling</term>
                <term xml:lang="en">Genetic Edition</term>
                <term xml:lang="en">Encoding Variants</term>
                <term xml:lang="en">Historical Manuscripts</term>
              </keywords>
              <classCode scheme="halDomain" n="shs.litt">Humanities and Social Sciences/Literature</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</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>Alterations in historical manuscripts such as letters represent a promising field of research. On the one hand, they help understand the construction of text. On the other hand, topics that are being considered sensitive at the time of the manuscript gain coherence and contextuality when taking alterations into account, especially in the case of deletions. The analysis of alterations in manuscripts, though, is a traditionally very tedious work. In this paper, we present a machine learning-based approach to help categorize alterations in documents. In particular, we present a new probabilistic model (Alteration Latent Dirichlet Allocation, alterLDA in the following) that categorizes content-related alterations. The method proposed here is developed based on experiments carried out on the digital scholarly edition Berlin Intellectuals, for which alterLDA achieves high performance in the recognition of alterations on labelled data. On unlabelled data, applying alterLDA leads to interesting new insights into the alteration behavior of authors, editors and other manuscript contributors, as well as insights into sensitive topics in the correspondence of Berlin intellectuals around 1800. In addition to the findings based on the digital scholarly edition Berlin Intellectuals, we present a general framework for the analysis of text genesis that can be used in the context of other digital resources representing document variants. To that end, we present in detail the methodological steps that are to be followed in order to achieve such results, giving thereby a prime example of an Machine Learning application the Digital Humanities.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-86624" status="VALID">
          <idno type="ROR">https://ror.org/03v4gjf40</idno>
          <orgName>Technical University of Berlin / Technische Universität Berlin</orgName>
          <orgName type="acronym">TUB</orgName>
          <date type="start">1946-01-01</date>
          <desc>
            <address>
              <addrLine>Straße des 17. Juni 135 10623 Berlin</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.tu.berlin/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-182700" status="VALID">
          <idno type="IdRef">148928641</idno>
          <idno type="ISNI">0000 0001 2291 6181</idno>
          <idno type="RNSR">200815564M</idno>
          <idno type="ROR">https://ror.org/03hq2nj16</idno>
          <idno type="Wikidata">Q51784243</idno>
          <orgName>Langues, Littératures, Linguistique des Universités d'Angers et du Mans</orgName>
          <orgName type="acronym">3L.AM</orgName>
          <date type="start">2008-01-01</date>
          <desc>
            <address>
              <addrLine>Le Mans Université, 3L.AM - UFR de Lettres, Langues et Sciences Humaines, MSH, Avenue Olivier Messiaen - 72085 Le Mans CEDEX 09Université d'Angers, 3L.AM - Faculté de Lettres, Langues et Sciences Humaines, Maison de la Recherche Germaine Tillion, 5 Bis Boulevard Lavoisier - 49045 Angers CEDEX 01</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://3lam.univ-lemans.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-7566" type="direct"/>
            <relation active="#struct-74911" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-7566" status="VALID">
          <idno type="ROR">https://ror.org/01mtcc283</idno>
          <orgName>Le Mans Université</orgName>
          <orgName type="acronym">UM</orgName>
          <desc>
            <address>
              <addrLine>Avenue Olivier Messiaen - 72085 Le Mans cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lemans.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-74911" status="VALID">
          <idno type="IdRef">026402920</idno>
          <idno type="ISNI">0000000122483363</idno>
          <idno type="ROR">https://ror.org/04yrqp957</idno>
          <orgName>Université d'Angers</orgName>
          <orgName type="acronym">UA</orgName>
          <date type="start">1971-10-25</date>
          <desc>
            <address>
              <addrLine>Université d'Angers - 40 Rue de Rennes, BP 73532 - 49035 Angers CEDEX 01</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-angers.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>