@inproceedings{lu-etal-2025-lemmatization,
    title = "Lemmatization of Cuneiform Languages Using the {B}y{T}5 Model",
    author = "Lu, Pengxiu  and
      Huang, Yonglong  and
      Xu, Jing  and
      Feng, Minxuan  and
      Xu, Chao",
    editor = "Anderson, Adam  and
      Gordin, Shai  and
      Li, Bin  and
      Liu, Yudong  and
      Passarotti, Marco C.  and
      Sprugnoli, Rachele",
    booktitle = "Proceedings of the Second Workshop on Ancient Language Processing",
    month = may,
    year = "2025",
    address = "The Albuquerque Convention Center, Laguna",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.alp-1.26/",
    pages = "197--205",
    ISBN = "979-8-89176-235-0",
    abstract = "Lemmatization of cuneiform languages presents a unique challenge due to their complex writing system, which combines syllabic and logographic elements. In this study, we investigate the effectiveness of the ByT5 model in addressing this challenge by developing and evaluating a ByT5-based lemmatization system. Experimental results demonstrate that ByT5 outperforms mT5 in this task, achieving an accuracy of 80.55{\%} on raw lemmas and 82.59{\%} on generalized lemmas, where sense numbers are removed. These findings highlight the potential of ByT5 for lemmatizing cuneiform languages and provide useful insights for future work on ancient text lemmatization."
}