@inproceedings{karagoz-etal-2024-towards,
    title = "Towards a Clean Text Corpus for {O}ttoman {T}urkish",
    author = {Karag{\"o}z, Fatih  and
      Do{\u{g}}an, Berat  and
      {\"O}zate{\c{s}}, {\c{S}}aziye Bet{\"u}l},
    editor = {Ataman, Duygu  and
      Derin, Mehmet Oguz  and
      Ivanova, Sardana  and
      K{\"o}ksal, Abdullatif  and
      S{\"a}lev{\"a}, Jonne  and
      Zeyrek, Deniz},
    booktitle = "Proceedings of the First Workshop on Natural Language Processing for Turkic Languages (SIGTURK 2024)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand and Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.sigturk-1.6/",
    pages = "62--70",
    abstract = "Ottoman Turkish, as a historical variant of modern Turkish, suffers from a scarcity of available corpora and NLP models. This paper outlines our pioneering endeavors to address this gap by constructing a clean text corpus of Ottoman Turkish materials. We detail the challenges encountered in this process and offer potential solutions. Additionally, we present a case study wherein the created corpus is employed in continual pre-training of BERTurk, followed by evaluation of the model{'}s performance on the named entity recognition task for Ottoman Turkish. Preliminary experimental results suggest the effectiveness of our corpus in adapting existing models developed for modern Turkish to historical Turkish."
}