Wasserstein Autoencoders with Mixture of Gaussian Priors for Stylized Text Generation

Amirpasha Ghabussi, Lili Mou, Olga Vechtomova

Abstract: Probabilistic autoencoders are effective for text generation. However, they are unable to control the style of generated text, despite the training samples explicitly labeled with different styles. We present a Wasserstein autoencoder with a Gaussian mixture prior for style-aware sentence generation. Our model is trained on a multi-class dataset and generates sentences in the style of the desired class. It is also capable of interpolating multiple classes. Moreover, we can train our model on relatively small datasets. While a regular WAE or VAE cannot generate diverse sentences with few training samples, our approach generates diverse sentences and preserves the style of the desired classes.