Learning Rhyming Constraints using Structured Adversaries
This addresses the challenge of generating structured poetry for natural language processing applications, but it is incremental as it builds on existing adversarial methods.
The paper tackled the problem of recurrent neural language models failing to capture rhyming patterns in poetry by proposing a generative adversarial setup with a structured discriminator, resulting in successful learning of rhyming constraints on Sonnet and Limerick datasets without phonetic information.
Existing recurrent neural language models often fail to capture higher-level structure present in text: for example, rhyming patterns present in poetry. Much prior work on poetry generation uses manually defined constraints which are satisfied during decoding using either specialized decoding procedures or rejection sampling. The rhyming constraints themselves are typically not learned by the generator. We propose an alternate approach that uses a structured discriminator to learn a poetry generator that directly captures rhyming constraints in a generative adversarial setup. By causing the discriminator to compare poems based only on a learned similarity matrix of pairs of line ending words, the proposed approach is able to successfully learn rhyming patterns in two different English poetry datasets (Sonnet and Limerick) without explicitly being provided with any phonetic information.