Emp-USIR: A Unidirectional Synchronous Interactive Reasoning Model for Empathetic Dialogue
Liting Jiang, Di Wu, Yanbing Li, Wushouer Silamu · 2023
The goal of an empathetic dialogue generative sys-tem is to generate coherently and relate emotional responses after finite turns of dialogue. Most of the previous work guided the dialogue system to generate empathetic responses from the dialogue history or emotional reasons. However, in people's daily communication, the empathetic response is often generated by deep reasoning through dialogue history and existing commonsense knowledge. To fill this gap, we propose an empathetic dialogue model of unidirectional synchronous interactive reasoning, Emp- Usir.Specifically, according to the existing commonsense knowledge base, we extract commonsense knowledge with emotional representation from it, and use it as the connection feature of dialogue history and remaining common-sense knowledge to guide the interactive reasoning between multi-turns dialogue history and commonsense knowledge, to imitate human reasoning based on commonsense to generate responses. Then, we propose a cross-token level attention mechanism to learn emotional dependence from reasoning features, to produce more smooth and diverse empathy responses. The experimental results and manual evaluation prove the effectiveness of the Emp-USIR model proposed in this paper on the widely-used benchmark dataset.