Log In Sign Up

Endowing Empathetic Dialogue Systems with Personas

by   Peixiang Zhong, et al.

Empathetic dialogue systems have been shown to improve user satisfaction and task outcomes in numerous domains. In Psychology, persona has been shown to be highly correlated to personality, which in turn influences empathy. In addition, our empirical analysis also suggests that persona plays an important role in empathetic dialogues. To this end, we propose a new task to endow empathetic dialogue systems with personas and present the first empirical study on the impacts of persona on empathetic responding. Specifically, we first present a novel large-scale multi-domain dataset for empathetic dialogues with personas. We then propose CoBERT, an efficient BERT-based response selection model that obtains the state-of-the-art performance on our dataset. Finally, we conduct extensive experiments to investigate the impacts of persona on empathetic responding. Notably, our results show that persona improves empathetic responding more when CoBERT is trained on empathetic dialogues than non-empathetic ones, establishing an empirical link between persona and empathy in human dialogues.


page 1

page 2

page 3

page 4


Endowing Empathetic Conversational Models with Personas

Empathetic conversational models have been shown to improve user satisfa...

Towards Task-Oriented Dialogue in Mixed Domains

This work investigates the task-oriented dialogue problem in mixed-domai...

Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems

Evaluation is crucial in the development process of task-oriented dialog...

A Data-driven Approach to Estimate User Satisfaction in Multi-turn Dialogues

The evaluation of multi-turn dialogues remains challenging. The common a...

Maintaining Common Ground in Dynamic Environments

Common grounding is the process of creating and maintaining mutual under...

Domain Transfer in Dialogue Systems without Turn-Level Supervision

Task oriented dialogue systems rely heavily on specialized dialogue stat...