You Impress Me: Dialogue Generation via Mutual Persona Perception
This addresses the need for more engaging and consistent dialogue systems in AI, though it is incremental as it builds on existing personalized dialogue methods.
The paper tackled the problem of improving chit-chat dialogue systems by modeling mutual understanding between interlocutors, proposing P^2 Bot, which enhanced personalized dialogue generation and achieved a considerable boost over state-of-the-art baselines on the Persona-Chat dataset.
Despite the continuing efforts to improve the engagingness and consistency of chit-chat dialogue systems, the majority of current work simply focus on mimicking human-like responses, leaving understudied the aspects of modeling understanding between interlocutors. The research in cognitive science, instead, suggests that understanding is an essential signal for a high-quality chit-chat conversation. Motivated by this, we propose P^2 Bot, a transmitter-receiver based framework with the aim of explicitly modeling understanding. Specifically, P^2 Bot incorporates mutual persona perception to enhance the quality of personalized dialogue generation. Experiments on a large public dataset, Persona-Chat, demonstrate the effectiveness of our approach, with a considerable boost over the state-of-the-art baselines across both automatic metrics and human evaluations.