Topic-Guided Variational Autoencoders for Text Generation

Understand

We propose a topic-guided variational autoencoder (TGVAE) model for text generation.

• Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Gaussian prior for the latent code, our model specifies the prior as a Gaussian mixture model (GMM) parametrized by a neural topic module.
• Each mixture component corresponds to a latent topic, which provides guidance to generate sentences under the topic.
• The neural topic module and the VAE-based neural sequence module in our model are learned jointly.