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

  title={End-to-End Reinforcement Learning of Dialogue Agents for Information Access},
  author={Bhuwan Dhingra and Lihong Li and Xiujun Li and Jianfeng Gao and Yun-Nung Chen and Faisal Ahmed and Li Deng},
This paper proposes KB-InfoBot1 — a multi-turn dialogue agent which helps users search Knowledge Bases (KBs) without composing complicated queries. Such goal-oriented dialogue agents typically need to interact with an external database to access 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 differentiability of the system and prevent endto-end training of… CONTINUE READING
Highly Cited
This paper has 86 citations. REVIEW CITATIONS
65 Citations
40 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 65 extracted citations

87 Citations

Citations per Year
Semantic Scholar estimates that this publication has 87 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 40 references

Similar Papers

Loading similar papers…