English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Variational autoencoders~(VAEs) have shown a promise in data-drivenconversation modeling. However, most VAE conversation models match theapproximate posterior distribution over the latent variables to a simple priorsuch as standard normal distribution, thereby restricting the generatedresponses to a relatively simple (e.g., unimodal) scope. In this paper, wepropose DialogWAE, a conditional Wasserstein autoencoder~(WAE) speciallydesigned for dialogue modeling. Unlike VAEs that impose a simple distributionover the latent variables, DialogWAE models the distribution of data bytraining a GAN within the latent variable space. Specifically, our modelsamples from the prior and posterior distributions over the latent variables bytransforming context-dependent random noise using neural networks and minimizesthe Wasserstein distance between the two distributions. We further develop aGaussian mixture prior network to enrich the latent space. Experiments on twopopular datasets show that DialogWAE outperforms the state-of-the-artapproaches in generating more coherent, informative and diverse responses.

DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder