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

Current variational dialog models have employed pre-trained language models(PLMs) to parameterize the likelihood and posterior distributions. However, theGaussian assumption made on the prior distribution is incompatible with thesedistributions, thus restricting the diversity of generated responses. Thesemodels also suffer from posterior collapse, i.e., the decoder tends to ignorelatent variables and directly access information captured in the encoderthrough the cross-attention mechanism. In this work, we propose Dior-CVAE, ahierarchical conditional variational autoencoder (CVAE) with diffusion priorsto address these challenges. We employ a diffusion model to increase thecomplexity of the prior distribution and its compatibility with thedistributions produced by a PLM. Also, we propose memory dropout to thecross-attention mechanism, which actively encourages the use of latentvariables for response generation. Overall, experiments across two commonlyused open-domain dialog datasets show that our method can generate more diverseresponses without large-scale dialog pre-training. Code is available athttps://github.com/UKPLab/dior-cvae.

Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation