Shaer: Controlled Arabic Poetry Generation with Meter Subform and Semantic Conditioning
We present Shaer, a controllable Classical Arabic poetry generation framework jointly conditioned on natural-language descriptions, meter subforms, and target hemistich counts.
Key points
- Classical Arabic poetry generation requires simultaneously satisfying semantic, linguistic, and fine-grained prosodic constraints.
- Existing systems typically control broad poetic attributes but do not jointly model semantic intent, meter subform, and poem length.
- To support this task, we construct an enriched corpus of 116,032 classical Arabic poems derived from Ashaar, containing normalized meter-subform labels and automatically generated, validated semantic descriptions.
- We then adapt Yehia-7B using QLoRA-based supervised fine-tuning with a completion-only objective.
Sources (1)
- [1]Shaer: Controlled Arabic Poetry Generation with Meter Subform and Semantic ConditioningarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 09:44 AM
We present Shaer, a controllable Classical Arabic poetry generation framework jointly conditioned on natural-language descriptions, meter subforms, and target hemistich counts.
Classical Arabic poetry generation requires simultaneously satisfying semantic, linguistic, and fine-grained prosodic constraints.
Extractive summary: sentences quoted from the sources.