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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

While recent neural encoder-decoder models have shown great promise inmodeling open-domain conversations, they often generate dull and genericresponses. Unlike past work that has focused on diversifying the output of thedecoder at word-level to alleviate this problem, we present a novel frameworkbased on conditional variational autoencoders that captures the discourse-leveldiversity in the encoder. Our model uses latent variables to learn adistribution over potential conversational intents and generates diverseresponses using only greedy decoders. We have further developed a novel variantthat is integrated with linguistic prior knowledge for better performance.Finally, the training procedure is improved by introducing a bag-of-word loss.Our proposed models have been validated to generate significantly more diverseresponses than baseline approaches and exhibit competence in discourse-leveldecision-making.

Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders