DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder

ICLR 2019 Xiaodong GuKyunghyun ChoJung-Woo HaSunghun Kim

Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling. However, most VAE conversation models match the approximate posterior distribution over the latent variables to a simple prior such as standard normal distribution, thereby restricting the generated responses to a relatively simple (e.g., unimodal) scope... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.