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

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, and outperform two commercially deployed customer-facing dialog systems.

Accepted as a long paper for the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017)

References in corpus (6)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• A Neural Conversational Model
• Deep Reinforcement Learning for Dialogue Generation
• Neural Responding Machine for Short-Text Conversation
• Attention with Intention for a Neural Network Conversation Model
• LSTM based Conversation Models

Cited by in corpus (4)

• Recent Advances and Challenges in Task-oriented Dialog System
• Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
• Controlled Language and Baby Turing Test for General Conversational Intelligence
• Natural Language Interaction to Facilitate Mental Models of Remote Robots