# Learning Rhyming Constraints using Structured Adversaries

arXiv: https://arxiv.org/abs/1909.06743 · HTML: https://mlsanity.com/paper/1909.06743/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models](https://mlsanity.com/paper/2212.10474/) (2022)
- [PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation](https://mlsanity.com/paper/2205.12206/) (2022)
- [Evaluating Diversity in Automatic Poetry Generation](https://mlsanity.com/paper/2406.15267/) (2024)
- [Does ChatGPT Have a Poetic Style?](https://mlsanity.com/paper/2410.15299/) (2024)
- [Metrical Tagging in the Wild: Building and Annotating Poetry Corpora with Rhythmic Features](https://mlsanity.com/paper/2102.08858/) (2021)
- [Prose2Poem: The Blessing of Transformers in Translating Prose to Persian Poetry](https://mlsanity.com/paper/2109.14934/) (2021)
- [What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering](https://mlsanity.com/paper/2601.20164/) (2026)
- [GPoeT-2: A GPT-2 Based Poem Generator](https://mlsanity.com/paper/2205.08847/) (2022)
- [SongRewriter: A Chinese Song Rewriting System with Controllable Content and Rhyme Scheme](https://mlsanity.com/paper/2211.15037/) (2022)

## Abstract (arXiv)

Existing recurrent neural language models often fail to capture higher-level structure present in text: for example, rhyming patterns present in poetry. Much prior work on poetry generation uses manually defined constraints which are satisfied during decoding using either specialized decoding procedures or rejection sampling. The rhyming constraints themselves are typically not learned by the generator. We propose an alternate approach that uses a structured discriminator to learn a poetry generator that directly captures rhyming constraints in a generative adversarial setup. By causing the discriminator to compare poems based only on a learned similarity matrix of pairs of line ending words, the proposed approach is able to successfully learn rhyming patterns in two different English poetry datasets (Sonnet and Limerick) without explicitly being provided with any phonetic information.