Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts

TL;DR

This paper introduces a method for open domain dialogue generation that uses dialogue acts as policies to improve response quality and control, learned from human conversations and optimized with reinforcement learning.

Contribution

It proposes a novel framework combining dialogue acts with reinforcement learning to enhance and control open domain dialogue systems, outperforming existing methods.

Findings

Significant improvement in response quality over state-of-the-art methods

Effective management of dialogue flow using dialogue acts

Successful application in both simulation and real conversations

Abstract

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.