When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generation
This addresses the issue of unnatural conversations in multi-turn open-domain dialogue systems for users, though it is incremental as it adds a decision module to existing models.
The paper tackles the problem of boring dialogue systems by enabling chatbots to autonomously decide when to speak based on conversation context, resulting in improved dialogue quality and significantly higher accuracy in timing decisions as shown in experiments on two benchmarks.
Despite the multi-turn open-domain dialogue systems have attracted more and more attention and made great progress, the existing dialogue systems are still very boring. Nearly all the existing dialogue models only provide a response when the user's utterance is accepted. But during daily conversations, humans always decide whether to continue to utter an utterance based on the context. Intuitively, a dialogue model that can control the timing of talking autonomously based on the conversation context can chat with humans more naturally. In this paper, we explore the dialogue system that automatically controls the timing of talking during the conversation. Specifically, we adopt the decision module for the existing dialogue models. Furthermore, modeling conversation context effectively is very important for controlling the timing of talking. So we also adopt the graph neural networks to process the context with the natural graph structure. Extensive experiments on two benchmarks show that controlling the timing of talking can effectively improve the quality of dialogue generation, and the proposed methods significantly improve the accuracy of the timing of talking. In addition, we have publicly released the codes of our proposed model.