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}
}