30 Ağustos 2024 Konferans bildirisi Açık Erişim

Bilgin Taşdemir, Esma F.; Tandoğan, Zeynep; Akansu, S. Doğan; Kızılırmak, Fırat; Şen, Umut; Akca, Aysu; Kuru, Mehmet; Yanıkoğlu, Berrin

DataCite XML

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.48623/aperta.274262</identifier>
  <creators>
    <creator>
      <creatorName>Bilgin Taşdemir, Esma F.</creatorName>
      <givenName>Esma F.</givenName>
      <familyName>Bilgin Taşdemir</familyName>
      <affiliation>Medeniyet Üniversitesi</affiliation>
    </creator>
    <creator>
      <creatorName>Tandoğan, Zeynep</creatorName>
      <givenName>Zeynep</givenName>
      <familyName>Tandoğan</familyName>
    </creator>
    <creator>
      <creatorName>Akansu, S. Doğan</creatorName>
      <givenName>S. Doğan</givenName>
      <familyName>Akansu</familyName>
    </creator>
    <creator>
      <creatorName>Kızılırmak, Fırat</creatorName>
      <givenName>Fırat</givenName>
      <familyName>Kızılırmak</familyName>
    </creator>
    <creator>
      <creatorName>Şen, Umut</creatorName>
      <givenName>Umut</givenName>
      <familyName>Şen</familyName>
      <affiliation>Sabancı Üniversitesi</affiliation>
    </creator>
    <creator>
      <creatorName>Akca, Aysu</creatorName>
      <givenName>Aysu</givenName>
      <familyName>Akca</familyName>
      <affiliation>Viyana Üniversitesi</affiliation>
    </creator>
    <creator>
      <creatorName>Kuru, Mehmet</creatorName>
      <givenName>Mehmet</givenName>
      <familyName>Kuru</familyName>
      <affiliation>Sabancı Üniversitesi</affiliation>
    </creator>
    <creator>
      <creatorName>Yanıkoğlu, Berrin</creatorName>
      <givenName>Berrin</givenName>
      <familyName>Yanıkoğlu</familyName>
      <affiliation>Sabancı Üniversitesi</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Automatic Transcription Of Ottoman Documents Using Deep Learning</title>
  </titles>
  <publisher>Aperta</publisher>
  <publicationYear>2024</publicationYear>
  <subjects>
    <subject>Ottoman Document Recognition</subject>
    <subject>Deep Learning</subject>
    <subject>Transcription</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2024-08-30</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://aperta.ulakbim.gov.tr/record/274262</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.48623/aperta.274261</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="http://www.opendefinition.org/licenses/cc-by-sa">Creative Commons Attribution Share-Alike</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;With the accelerated pace of digitization, a vast collection of Ottoman documents has become accessible to researchers and the general public. However, most users interested in these documents are unable to read them, as the text is Turkish written in the Arabic-Persian script. Manual transcription of such a massive amount of documents is also beyond the capacity of human experts. With the advancements in deep learning, we have been able to provide a solution to the long-standing problem of automatic transcription of printed Ottoman documents. We evaluated three decoding strategies including Word Beam Search that allows to use a recognition lexicon and n-gram statistics during the decoding phase. Furthermore, the effect of lexicon size and coverage and language modelling via character or word n-grams are also evaluated. Using a general purpose large lexicon of the Ottoman era (260K words and 86% test coverage), the performance is measured as 6.59% character error rate and 28.46% word error rate on a test set of 6, 828 text lines.&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>Türkiye Bilimsel ve Teknolojik Araştirma Kurumu</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">https://doi.org/10.13039/501100004410</funderIdentifier>
      <awardNumber>122E399</awardNumber>
    </fundingReference>
  </fundingReferences>
</resource>