% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{en:281367,
      author       = {Şen, Mehmet Umut and Bilecen, Ali and Bilgin Taşdemir,
                      Esma Fatıma and Yanıkoğlu, Berrin},
      title        = {{T}ranscription of {O}ttoman {D}ocuments using
                      {T}ransformer {B}ased {M}odels | {O}smanlica {D}ok manlarin
                      {D} n st r c {T}abanli {M}odeller ile {T}ranskripsiyonu},
      publisher    = {IEEE},
      reportid     = {DZNE-2025-01114},
      pages        = {1 - 4},
      year         = {2025},
      comment      = {2025 33rd Signal Processing and Communications Applications
                      Conference (SIU) : [Proceedings] - IEEE, 2025. - ISBN
                      979-8-3315-6655-5 - doi:10.1109/SIU66497.2025.11112382},
      booktitle     = {2025 33rd Signal Processing and
                       Communications Applications Conference
                       (SIU) : [Proceedings] - IEEE, 2025. -
                       ISBN 979-8-3315-6655-5 -
                       doi:10.1109/SIU66497.2025.11112382},
      abstract     = {Although access to a large number of Ottoman documents has
                      become easier today, the Arabic-Persian-based Ottoman script
                      remains a barrier for interested users in utilizing these
                      documents. To address this challenge, there is a need for
                      automatic transcription systems. While some deep
                      learning-based commercial and academic models exist for
                      Ottoman transcription, no studies have yet explored models
                      based on transformer architectures. This paper introduces an
                      Ottoman transcription system developed using TrOCR, a
                      transformer-based model. Instead of the commonly used
                      two-step approach in the literature, a model was designed to
                      perform both optical character recognition and transcription
                      into Turkish in one step. Additionally, the decoder
                      responsible for language modeling was initialized with a
                      BERT-based model trained on Turkish data, achieving results
                      comparable to the original model. During testing, this model
                      produced outputs more quickly due to improved tokenization
                      performance.},
      month         = {Jun},
      date          = {2025-06-25},
      organization  = {33rd Signal Processing and
                       Communications Applications Conference,
                       Sile (Istanbul), 25 Jun 2025 - 28 Jun
                       2025},
      cin          = {AG Gokce},
      cid          = {I:(DE-2719)1013041},
      pnm          = {351 - Brain Function (POF4-351)},
      pid          = {G:(DE-HGF)POF4-351},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      doi          = {10.1109/SIU66497.2025.11112382},
      url          = {https://pub.dzne.de/record/281367},
}