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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Neural end-to-end goal-oriented dialog systems showed promise to reduce theworkload of human agents for customer service, as well as reduce wait time forusers. However, their inability to handle new user behavior at deployment haslimited their usage in real world. In this work, we propose an end-to-endtrainable method for neural goal-oriented dialog systems which handles new userbehaviors at deployment by transferring the dialog to a human agentintelligently. The proposed method has three goals: 1) maximize user's tasksuccess by transferring to human agents, 2) minimize the load on the humanagents by transferring to them only when it is essential and 3) learn onlinefrom the human agent's responses to reduce human agents load further. Weevaluate our proposed method on a modified-bAbI dialog task that simulates thescenario of new user behaviors occurring at test time. Experimental resultsshow that our proposed method is effective in achieving the desired goals.

Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use