MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
arXiv:2003.06094
Abstract
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.
arXiv comment8 pages, 5 figures, published in AAAI 2020
References in corpus (9)
- Auto-Encoding Variational Bayes
- Spectral Normalization for Generative Adversarial Networks
- Categorical Reparameterization with Gumbel-Softmax
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- cGANs with Projection Discriminator
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Learning in Implicit Generative Models
- Toward Controlled Generation of Text
- Chinese Poetry Generation with a Working Memory Model