@inproceedings{qaddoumi-etal-2026-learning,
    title = "Learning Stress in {A}rabic Low-Resource Settings",
    author = "Qaddoumi, Abed  and
      Kodner, Jordan  and
      Rambow, Owen  and
      Khalifa, Salam  and
      Heinz, Jeffrey",
    editor = "Voigt, Rob  and
      Warstadt, Alex  and
      Feldman, Naomi  and
      Linzen, Tal",
    booktitle = "Proceedings of the Society for Computation in Linguistics 2026",
    month = jul,
    year = "2026",
    address = "San Diego, CA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.scil-main.24/",
    pages = "262--279",
    ISBN = "979-8-89176-412-5",
    abstract = "We predict lexical stress in Arabic varieties using syllable structure (a sequence of CVs, with C for consonants and V for vowels). Our task is generation: given an unstressed input, the system outputs a stress-marked word. We compare four approaches: a grammar induction algorithm (BUFIA), a transformer-based neural network (NN), a rule-based method, and a frequency baseline. The models are evaluated across several low-resource settings by varying the training data size by words, structural type, and syllable count. BUFIA outperforms the neural network, especially when data are scarce. This supports grammar induction as an interpretable and sample-efficient alternative for learning stress."
}