@InProceedings{dhingra-EtAl:2017:Long1,
  author    = {Dhingra, Bhuwan  and  Li, Lihong  and  Li, Xiujun  and  Gao, Jianfeng  and  Chen, Yun-Nung  and  Ahmed, Faisal  and  Deng, Li},
  title     = {Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {484--495},
  abstract  = {This paper proposes KB-InfoBot - 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 end-to-end training of neural dialogue agents. In this
	paper, we address this limitation by replacing symbolic queries with an induced
	``soft'' posterior distribution 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
	simulations 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.},
  url       = {http://aclweb.org/anthology/P17-1045}
}