Abstract
Poetry generation, and creative language generation in general, usually suffers from the lack of large training data. In this paper, we present a novel framework to generate sonnets that does not require training on poems. We design a hierarchical framework which plans the poem sketch before decoding. Specifically, a content planning module is trained on non-poetic texts to obtain discourse-level coherence; then a rhyme module generates rhyme words and a polishing module introduces imagery and similes for aesthetics purposes. Finally, we design a constrained decoding algorithm to impose the meter-and-rhyme constraint of the generated sonnets. Automatic and human evaluation show that our multi-stage approach without training on poem corpora generates more coherent, poetic, and creative sonnets than several strong baselines.- Anthology ID:
- 2022.naacl-main.262
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3587–3597
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.262
- DOI:
- 10.18653/v1/2022.naacl-main.262
- Cite (ACL):
- Yufei Tian and Nanyun Peng. 2022. Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3587–3597, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features (Tian & Peng, NAACL 2022)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2022.naacl-main.262.pdf
- Code
- pluslabnlp/sonnet-gen