MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
This work addresses the issue of low diversity in poetry generation for AI creativity applications, representing an incremental advancement by integrating multiple factors into a neural model.
The authors tackled the problem of poor diversity in automatic poetry generation by proposing MixPoet, a model that learns a controllable mixed latent space to incorporate multiple influence factors, resulting in improved diversity and quality in Chinese poetry generation compared to three state-of-the-art models.
As an essential step towards computer creativity, automatic poetry generation has gained increasing attention these years. Though recent neural models make prominent progress in some criteria of poetry quality, generated poems still suffer from the problem of poor diversity. Related literature researches show that different factors, such as life experience, historical background, etc., would influence composition styles of poets, which considerably contributes to the high diversity of human-authored poetry. Inspired by this, we propose MixPoet, a novel model that absorbs multiple factors to create various styles and promote diversity. Based on a semi-supervised variational autoencoder, our model disentangles the latent space into some subspaces, with each conditioned on one influence factor by adversarial training. In this way, the model learns a controllable latent variable to capture and mix generalized factor-related properties. Different factor mixtures lead to diverse styles and hence further differentiate generated poems from each other. Experiment results on Chinese poetry demonstrate that MixPoet improves both diversity and quality against three state-of-the-art models.