Generate and Revise: Reinforcement Learning in Neural Poetry

TL;DR

This paper introduces a reinforcement learning framework for iterative poem generation and revision, mimicking human editing to improve poetic quality while respecting formal constraints like rhyme and meter.

Contribution

It presents a novel RL-based method using Proximal Policy Optimization for generating and revising poems without explicit rhyme guidance, applicable to broader text generation tasks.

Findings

Effective in matching rhyming schemes without explicit rhyme info

Generates high-quality poems through iterative revision

Framework adaptable to other text generation problems

Abstract

Writers, poets, singers usually do not create their compositions in just one breath. Text is revisited, adjusted, modified, rephrased, even multiple times, in order to better convey meanings, emotions and feelings that the author wants to express. Amongst the noble written arts, Poetry is probably the one that needs to be elaborated the most, since the composition has to formally respect predefined meter and rhyming schemes. In this paper, we propose a framework to generate poems that are repeatedly revisited and corrected, as humans do, in order to improve their overall quality. We frame the problem of revising poems in the context of Reinforcement Learning and, in particular, using Proximal Policy Optimization. Our model generates poems from scratch and it learns to progressively adjust the generated text in order to match a target criterion. We evaluate this approach in the case of matching a rhyming scheme, without having any information on which words are responsible of creating rhymes and on how to coherently alter the poem words. The proposed framework is general and, with an appropriate reward shaping, it can be applied to other text generation problems.