# A Rhythm-Aware Phrase Insertion for Classical Arabic Poetry Composition

arXiv: https://arxiv.org/abs/2509.18514 · HTML: https://mlsanity.com/paper/2509.18514/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [AraGPT2: Pre-Trained Transformer for Arabic Language Generation](https://mlsanity.com/paper/2012.15520/) (2020)
- [Learning meters of Arabic and English poems with Recurrent Neural Networks: a step forward for language understanding and synthesis](https://mlsanity.com/paper/1905.05700/) (2019)
- [AraPoemBERT: A Pretrained Language Model for Arabic Poetry Analysis](https://mlsanity.com/paper/2403.12392/) (2024)
- [Let the Poem Hit the Rhythm: Using a Byte-Based Transformer for Beat-Aligned Poetry Generation](https://mlsanity.com/paper/2406.10174/) (2024)

## Built on by (most cited first, 2 of 2)

- [Instruction-Guided Poetry Generation in Arabic and Its Dialects](https://mlsanity.com/paper/2604.27766/) (2026)
- [Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomy](https://mlsanity.com/paper/2607.18984/) (2026)

## Abstract (arXiv)

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.