A Rhythm-Aware Phrase Insertion for Classical Arabic Poetry Composition
This work addresses the challenge of automated classical Arabic poetry composition, which is incremental as it builds on existing multilingual transformer models with tailored rules and training strategies.
The paper tackled the problem of inserting phrases into Arabic poems to match a specific rhythm, achieving high rhythmic alignment while maintaining semantic coherence.
This paper presents a methodology for inserting phrases in Arabic poems to conform to a specific rhythm using ByT5, a byte-level multilingual transformer-based model. Our work discusses a rule-based grapheme-to-beat transformation tailored for extracting the rhythm from fully diacritized Arabic script. Our approach employs a conditional denoising objective to fine-tune ByT5, where the model reconstructs masked words to match a target rhythm. We adopt a curriculum learning strategy, pre-training on a general Arabic dataset before fine-tuning on poetic dataset, and explore cross-lingual transfer from English to Arabic. Experimental results demonstrate that our models achieve high rhythmic alignment while maintaining semantic coherence. The proposed model has the potential to be used in co-creative applications in the process of composing classical Arabic poems.