mlsanityData to 14 Oct 2026

Let the Poem Hit the Rhythm: Using a Byte-Based Transformer for Beat-Aligned Poetry Generation

arXiv 2406.10174 ↗First posted 14 Jun 2024cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

The intersection between poetry and music provides an interesting case for computational creativity, yet remains relatively unexplored. This paper explores the integration of poetry and music through the lens of beat patterns, investigating whether a byte-based language model can generate words that fit specific beat patterns within the context of poetry. Drawing on earlier studies, we developed a method to train a byte-based transformer model, ByT5, to align poems with beat patterns. The results demonstrate a high level of beat alignment while maintaining semantic coherence. Future work will aim to improve the model's ability to create complete beat-aligned poems.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 8 of its 20 references that are in the map. First posted on arXiv 14 Jun 2024.

Builds on

8 of 20 references.

References · 8

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  3. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 834
  4. 2021ByT5: Towards a token-free future with pre-trained byte-to-byte modelscited by 509
  5. 2020SongMASS: Automatic Song Writing with Pre-training and Alignment Constraintcited by 41
  6. 2021DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modelingcited by 25
  7. 2022ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Modelscited by 25
  8. 2021Metrical Tagging in the Wild: Building and Annotating Poetry Corpora with Rhythmic Featurescited by 8

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025A Rhythm-Aware Phrase Insertion for Classical Arabic Poetry Compositioncited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024SongGLM: Lyric-to-Melody Generation with 2D Alignment Encoding and Multi-Task Pre-Training
  2. 2023In BLOOM: Creativity and Affinity in Artificial Lyrics and Art
  3. 2025JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment
  4. 2025Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation
  5. 2026MIDI-REPA: Improving Text-to-Music Generation with Symbolic Representation Alignment
  6. 2023Mousai: Text-to-Music Generation with Long-Context Latent Diffusion
  7. 2025ACE-Step: A Step Towards Music Generation Foundation Model
  8. 2025SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement