@InProceedings{williams-asadi-zweig:2017:Long,
  author    = {Williams, Jason D  and  Asadi, Kavosh  and  Zweig, Geoffrey},
  title     = {Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning},
  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     = {665--677},
  abstract  = {End-to-end learning of recurrent neural networks (RNNs) is an attractive
	solution for dialog systems; however, current techniques are data-intensive and
	require thousands of dialogs to learn simple behaviors.  We introduce Hybrid
	Code Networks (HCNs), which combine an RNN with domain-specific knowledge
	encoded as software and system action templates. Compared to existing
	end-to-end approaches, HCNs considerably reduce the amount of training data
	required, while retaining the key benefit of inferring a latent representation
	of dialog state. In addition, HCNs can be optimized with supervised learning,
	reinforcement learning, or a mixture of both. HCNs attain state-of-the-art
	performance on the bAbI dialog dataset (Bordes and Weston, 2016), and
	outperform two commercially deployed customer-facing dialog systems at our
	company.},
  url       = {http://aclweb.org/anthology/P17-1062}
}