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

This paper proposes KB-InfoBot -- a multi-turn dialogue agent which helpsusers search Knowledge Bases (KBs) without composing complicated queries. Suchgoal-oriented dialogue agents typically need to interact with an externaldatabase to access real-world knowledge. Previous systems achieved this byissuing a symbolic query to the KB to retrieve entries based on theirattributes. However, such symbolic operations break the differentiability ofthe system and prevent end-to-end training of neural dialogue agents. In thispaper, we address this limitation by replacing symbolic queries with an induced"soft" posterior distribution over the KB that indicates which entities theuser is interested in. Integrating the soft retrieval process with areinforcement learner leads to higher task success rate and reward in bothsimulations and against real users. We also present a fully neural end-to-endagent, trained entirely from user feedback, and discuss its application towardspersonalized dialogue agents. The source code is available athttps://github.com/MiuLab/KB-InfoBot.

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access