English

Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features

Computation and Language 2022-05-05 v1 Artificial Intelligence Machine Learning

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.

Cite

@article{arxiv.2205.01821,
  title  = {Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features},
  author = {Yufei Tian and Nanyun Peng},
  journal= {arXiv preprint arXiv:2205.01821},
  year   = {2022}
}

Comments

To appear in NAACL 2022

R2 v1 2026-06-24T11:06:32.941Z