Paper

Learning Stress in Arabic Low-Resource Settings

---

Abstract

We predict lexical stress in Arabic varieties from syllable structure, modeling stress assignment as 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, a rule-based method derived from linguistic literature, 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 points to grammar induction as an interpretable and sample-efficient approach for learning stress.

Keywords: Arabic, stress, low-resource, learning, grammar induction, BUFIA, neural transduction, dialects, syllable, phonology, FSA

How to Cite:

Qaddoumi, A., Rambow, O., Kodner, J., Heinz, J. & Khalifa, S., (2026) “Learning Stress in Arabic Low-Resource Settings”, Society for Computation in Linguistics 9(1). doi: https://doi.org/10.7275/scil.4056