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. Society for Computation in Linguistics, 9(1)