@inproceedings{nigatu-etal-2025-case,
    title = "A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the {G}e{'}ez Script.",
    author = "Nigatu, Hellina Hailu  and
      Tonja, Atnafu Lambebo  and
      Ademtew, Henok Biadglign  and
      Alemayehu, Hizkiel Mitiku  and
      Abadi, Negasi Haile  and
      Belay, Tadesse Destaw  and
      Yimam, Seid Muhie",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.523/",
    pages = "10320--10331",
    ISBN = "979-8-89176-332-6",
    abstract = "Homophone normalization{--}where characters that have the same sound in a writing script are mapped to one character{--}is a pre-processing step applied in Amharic Natural Language Processing (NLP) literature. While this may improve performance reported by automatic metrics, it also results in models that are unable to effectively process different forms of writing in a single language. Further, there might be impacts in transfer learning, where models trained on normalized data do not generalize well to other languages. In this paper, we experiment with monolingual training and cross-lingual transfer to understand the impacts of normalization on languages that use the Ge{'}ez script. We then propose a post-inference intervention in which normalization is applied to model predictions instead of training data. With our simple scheme of post-inference normalization, we show that we can achieve an increase in BLEU score of up to 1.03 while preserving language features in training."
}