Generate and Revise: Reinforcement Learning in Neural Poetry
This work addresses the problem of generating high-quality, formally constrained poetry for AI systems, offering an incremental approach to text revision.
This paper proposes a reinforcement learning framework using Proximal Policy Optimization to generate and revise poems. The model learns to progressively adjust generated text to match a target criterion, specifically a rhyming scheme, without explicit information on rhyming words or alteration methods.
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.