Lee, J. Y., Aik Lee, K., & Gan, W. S. (2022). Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp43922.2022.9747458
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.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done