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

Anonymous

Paper Link: https://openreview.net/forum?id=6wKqI-x0Vb

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

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.

Presentation Mode: This paper will be presented in person in Seattle

Copyright Consent Signature (type Name Or NA If Not Transferrable): Yufei Tian

Copyright Consent Name And Address: UCLA, 405 Hilgard Avenue, Los Angeles, CA