Lune

EMNLP Findings2022

PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation

Aitor Ormazabal, Mikel Artetxe, Manex Agirrezabal, Aitor Soroa, Eneko Agirre

Abstract

Formal verse poetry imposes strict constraints on the meter and rhyme scheme of poems. Most prior work on generating this type of poetry uses existing poems for supervision, which are difficult to obtain for most languages and poetic forms. In this work, we propose an unsupervised approach to generate poems that follow any given meter and rhyme scheme, without requiring any poetic text for training. Our method works by splitting a regular, non-poetic corpus into phrases, prepending control codes that describe the length and end rhyme of each phrase, and training a transformer language model in the augmented corpus. The transformer learns to link the structure descriptor with the control codes to the number of lines, their length and their end rhyme. During inference, we build control codes for the desired meter and rhyme scheme, and condition our language model on them to generate formal verse poetry. Experiments in Spanish and Basque show that our approach is able to generate valid poems, which are often comparable in quality to those written by humans.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

8 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Help me write a Poem - Instruction Tuning as a Vehicle for Collaborative Poetry Writing cites Automatic Poetry Generation from Prosaic Text
  • Towards Enhanced Immersion and Agency for LLM-based Interactive Drama cites Help me write a Poem - Instruction Tuning as a Vehicle for Collaborative Poetry Writing
  • DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling cites Automatic Poetry Generation from Prosaic Text
  • ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models cites Automatic Poetry Generation from Prosaic Text
  • ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models cites DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers8

  1. Help me write a Poem - Instruction Tuning as a Vehicle for Collaborative Poetry WritingTuhin Chakrabarty, Vishakh Padmakumar, He HeEMNLP 2022 · 42 citations
  2. Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language ArtsTaewook Kim, Hyomin Han, Eytan Adar, Matthew Kay et al.CHI 2024 · 20 citations
  3. ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language ModelsJonas Belouadi, Steffen EgerACL 2023 · 12 citations
  4. Towards Enhanced Immersion and Agency for LLM-based Interactive DramaHongqiu Wu, Weiqi Wu, Tianyang Xu, Jiameng Zhang et al.ACL 2025 · 7 citations
  5. What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answeringJim Maar, Denis Paperno, Callum McDougall, Neel NandaICLR 2026 · 6 citations

Builds on3

  1. Automatic Poetry Generation from Prosaic TextTim Van de CruysACL 2020 · 54 citations
  2. Controlling Machine Translation for Multiple Attributes with Additive InterventionsAndrea Schioppa, David Vilar, Artem Sokolov, Katja FilippovaEMNLP 2021 · 16 citations
  3. DeepRapper: Neural Rap Generation with Rhyme and Rhythm ModelingLanqing Xue, Kaitao Song, Duocai Wu, Xu Tan et al.ACL 2021

Related papers

  1. Sonnet or Not, Bot? Poetry Evaluation for Large Models and DatasetsMelanie Walsh, Maria Antoniak, Anna PreusEMNLP Findings 2024 · 10 citations
  2. Don't Go Far Off: An Empirical Study on Neural Poetry TranslationTuhin Chakrabarty, Arkadiy Saakyan, Smaranda MuresanEMNLP 2021 · 8 citations
  3. Evaluating Diversity in Automatic Poetry GenerationYanran Chen, Hannes Gröner, Sina Zarrieß, Steffen EgerEMNLP 2024 · 3 citations
  4. Rigid Formats Controlled Text GenerationPiji Li, Haisong Zhang, Xiaojiang Liu, Shuming ShiACL 2020 · 2 citations
  5. Detach and Attach: Stylized Image Captioning without Paired Stylized DatasetYutong Tan, Zheng Lin, Peng Fu, Mingyu Zheng et al.ACM MM 2022 · 8 citations
Dusk over the sea between two cliffs drawn in fine vertical lines