Pith. sign in

DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

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. In this paper, we propose DialogWAE, a conditional Wasserstein autoencoder~(WAE) specially designed for dialogue modeling. Unlike VAEs that impose a simple distribution over the latent variables, DialogWAE models the distribution of data by training a GAN within the latent variable space. Specifically, our model samples from the prior and posterior distributions over the latent variables by transforming context-dependent random noise using neural networks and minimizes the Wasserstein distance between the two distributions. We further develop a Gaussian mixture prior network to enrich the latent space. Experiments on two popular datasets show that DialogWAE outperforms the state-of-the-art approaches in generating more coherent, informative and diverse responses.

fields

cs.CL 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • Mixture Content Selection for Diverse Sequence Generation cs.CL · 2019-09-04 · conditional · none · ref 14 · internal anchor

    A mixture-of-experts content selector that masks different input tokens for each generated sequence improves diversity and accuracy in question generation and summarization.