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

We investigate response generation for multi-turn dialogue ingenerative-based chatbots. Existing generative models based on RNNs (RecurrentNeural Networks) usually employ the last hidden state to summarize thesequences, which makes models unable to capture the subtle variability observedin different dialogues and cannot distinguish the differences between dialoguesthat are similar in composition. In this paper, we propose a Pseudo-VariationalGated Recurrent Unit (PVGRU) component without posterior knowledge throughintroducing a recurrent summarizing variable into the GRU, which can aggregatethe accumulated distribution variations of subsequences. PVGRU can perceive thesubtle semantic variability through summarizing variables that are optimized bythe devised distribution consistency and reconstruction objectives. Inaddition, we build a Pseudo-Variational Hierarchical Dialogue (PVHD) modelbased on PVGRU. Experimental results demonstrate that PVGRU can broadly improvethe diversity and relevance of responses on two benchmark datasets.

PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism