@inproceedings{beekhuizen-2025-vorm,
    title = "Vorm: Translations and a constrained hypothesis space support unsupervised morphological segmentation across languages",
    author = "Beekhuizen, Barend",
    editor = "Boleda, Gemma  and
      Roth, Michael",
    booktitle = "Proceedings of the 29th Conference on Computational Natural Language Learning",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.conll-1.39/",
    pages = "602--626",
    ISBN = "979-8-89176-271-8",
    abstract = "This paper introduces Vorm, an unsupervised morphological segmentation system, leveraging translation data to infer highly accurate morphological transformations, including less-frequently modeled processes such as infixation and reduplication. The system is evaluated on standard benchmark data and a novel, typologically diverse, dataset of 37 languages. Model performance is competitive and sometimes superior on canonical segmentation, but more limited on surface segmentation."
}