View Project

Title:

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

Abstract:

This paper proposes KB-InfoBot — a multi-turn dialogue agent w hich helps users search Knowledge Bases (KBs) without composing complicated queries. Such goal-oriented dialogue agents typically need to interact with an external database to a ccess real-world knowledge. Previous systems achieved this by issuing a symbolic query to the KB to retrieve entries based on their attributes. However, such symbolic operations break the differ entiability of the system and prevent end-to-end training of neural dialogue agents. In this paper, we address this limitation by replacing symbolic queries with an induced “soft” posterior dist ribution over the KB that indicates which entities the user is interested in. Integrating the soft retrieval process with a reinforcement learner leads to higher task success rate and reward in both s imulations and against real users. We also present a fully neural end-to-end agent, trained entirely from user feedback, and discuss its application towards personalized dialogue agents.

Comments:

Actions

Suggested Topics

Full Matches (full topic name in abstract)

Partial Matches (at least half of words topic name appear in abstract)

Suggested Resources

Uses abstract to search the content of resources available in Topics. Sorted by relevance.

# Title Author Topic Medium Score