@inproceedings{riemenschneider-2025-beyond,
    title = "Beyond Base Predictors: Using {LLM}s to Resolve Ambiguities in {A}kkadian Lemmatization",
    author = "Riemenschneider, Frederick",
    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/moar-dois/2025.alp-1.30/",
    doi = "10.18653/v1/2025.alp-1.30",
    pages = "226--231",
    ISBN = "979-8-89176-235-0",
    abstract = "We present a hybrid approach for Akkadian lemmatization in the EvaCun 2025 Shared Task that combines traditional NLP techniques with large language models (LLMs). Our system employs three Base Predictors{--}a dictionary lookup and two T5 models{--}to establish initial lemma candidates. For cases where these pre-dictors disagree (18.72{\%} of instances), we im-plement an LLM Resolution module, enhanced with direct access to the electronic Babylonian Library (eBL) dictionary entries. This module includes a Predictor component that generates initial lemma predictions based on dictionary information, and a Validator component that refines these predictions through contextual rea-soning. Error analysis reveals that the system struggles most with small differences (like cap-italization) and certain ambiguous logograms (like BI). Our work demonstrates the benefits of combining traditional NLP approaches with the reasoning capabilities of LLMs when provided with appropriate domain knowledge."
}