Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
This addresses the problem of generating more explainable and controllable social chat dialogues for AI systems, representing an incremental advancement.
The paper tackled open domain dialogue generation by using dialogue acts to manage interaction flow, achieving significant improvements in response quality and dialogue length over state-of-the-art methods in both simulated and human-machine conversations.
We study open domain dialogue generation with dialogue acts designed to explain how people engage in social chat. To imitate human behavior, we propose managing the flow of human-machine interactions with the dialogue acts as policies. The policies and response generation are jointly learned from human-human conversations, and the former is further optimized with a reinforcement learning approach. With the dialogue acts, we achieve significant improvement over state-of-the-art methods on response quality for given contexts and dialogue length in both machine-machine simulation and human-machine conversation.