Tahdib: A Rhythm-Aware Phrase Insertion for Classical Arabic Poetry Composition

Mohamad Elzohbi, Richard Zhao


Abstract
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.
Anthology ID:
2025.arabicnlp-main.15
Volume:
Proceedings of The Third Arabic Natural Language Processing Conference
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Kareem Darwish, Ahmed Ali, Ibrahim Abu Farha, Samia Touileb, Imed Zitouni, Ahmed Abdelali, Sharefah Al-Ghamdi, Sakhar Alkhereyf, Wajdi Zaghouani, Salam Khalifa, Badr AlKhamissi, Rawan Almatham, Injy Hamed, Zaid Alyafeai, Areeb Alowisheq, Go Inoue, Khalil Mrini, Waad Alshammari
Venue:
ArabicNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
194–202
Language:
URL:
https://aclanthology.org/2025.arabicnlp-main.15/
DOI:
Bibkey:
Cite (ACL):
Mohamad Elzohbi and Richard Zhao. 2025. Tahdib: A Rhythm-Aware Phrase Insertion for Classical Arabic Poetry Composition. In Proceedings of The Third Arabic Natural Language Processing Conference, pages 194–202, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Tahdib: A Rhythm-Aware Phrase Insertion for Classical Arabic Poetry Composition (Elzohbi & Zhao, ArabicNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.arabicnlp-main.15.pdf