Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning

Jason D. Williams, Kavosh Asadi, Geoffrey Zweig


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.
Anthology ID:
P17-1062
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
665–677
Language:
URL:
https://aclanthology.org/P17-1062
DOI:
10.18653/v1/P17-1062
Bibkey:
Cite (ACL):
Jason D. Williams, Kavosh Asadi, and Geoffrey Zweig. 2017. Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 665–677, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning (Williams et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1062.pdf
Video:
 https://vimeo.com/234957373
Code
 additional community code