@inproceedings{pavlopoulos-etal-2024-challenging,
    title = "Challenging Error Correction in Recognised Byzantine {G}reek",
    author = "Pavlopoulos, John  and
      Kougia, Vasiliki  and
      Garces Arias, Esteban  and
      Platanou, Paraskevi  and
      Shabalin, Stepan  and
      Liagkou, Konstantina  and
      Papadatos, Emmanouil  and
      Essler, Holger  and
      Camps, Jean-Baptiste  and
      Fischer, Franz",
    editor = "Pavlopoulos, John  and
      Sommerschield, Thea  and
      Assael, Yannis  and
      Gordin, Shai  and
      Cho, Kyunghyun  and
      Passarotti, Marco  and
      Sprugnoli, Rachele  and
      Liu, Yudong  and
      Li, Bin  and
      Anderson, Adam",
    booktitle = "Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)",
    month = aug,
    year = "2024",
    address = "Hybrid in Bangkok, Thailand and online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2024.ml4al-1.1/",
    doi = "10.18653/v1/2024.ml4al-1.1",
    pages = "1--12",
    abstract = "Automatic correction of errors in Handwritten Text Recognition (HTR) output poses persistent challenges yet to be fully resolved. In this study, we introduce a shared task aimed at addressing this challenge, which attracted 271 submissions, yielding only a handful of promising approaches. This paper presents the datasets, the most effective methods, and an experimental analysis in error-correcting HTRed manuscripts and papyri in Byzantine Greek, the language that followed Classical and preceded Modern Greek. By using recognised and transcribed data from seven centuries, the two best-performing methods are compared, one based on a neural encoder-decoder architecture and the other based on engineered linguistic rules. We show that the recognition error rate can be reduced by both, up to 2.5 points at the level of characters and up to 15 at the level of words, while also elucidating their respective strengths and weaknesses."
}