Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents

Abstract

In recent years, latent variable models, such as the Conditional Variational Auto Encoder (CVAE), have been applied to both personalized and empathetic dialogue generation. Prior work have largely focused on generating diverse dialogue responses that exhibit persona consistency and empathy. However, when it comes to the contextual coherence of the generated responses, there is still room for improvement. Hence, to improve the contextual coherence, we propose a novel Uncertainty Aware CVAE (UA-CVAE) framework. The UA-CVAE framework involves approximating and incorporating the aleatoric uncertainty during response generation. We apply our framework to both personalized and empathetic dialogue generation. Empirical results show that our framework significantly improves the contextual coherence of the generated response. Additionally, we introduce a novel automatic metric for measuring contextual coherence, which was found to correlate positively with human judgement.

Audio Embedding-Aware Dialogue Policy Learning

“…Furthermore, it can also serve as a tool to model long-term dialogue goals [12], which is a very novel trend on dialogue modelling [13]; and even for dialogue emotion recognition [14], [15], another contemporary research topic [16]. On the other hand, latent-variable models have also been adopted to build open domain dialogue systems that produce more diverse [17] or contextually coherent [18] responses. Moreover, these models have also attracted attention for task-oriented dialogue management, where they have been used for joint state tracking and dialogue response generation [19], and also combined with pretrained transformer language models [20].…”