Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents

TL;DR

This paper introduces UA-CVAE, a novel framework that incorporates uncertainty modeling to enhance the contextual coherence of personalized and empathetic dialogue responses, validated by a new automatic coherence metric.

Contribution

The paper proposes UA-CVAE, a new uncertainty-aware model that improves contextual coherence in dialogue generation and introduces a novel automatic coherence metric.

Findings

Significant improvement in contextual coherence of generated responses

Positive correlation between the new metric and human judgment

Effective application to both personalized and empathetic dialogue generation

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.