PAL: Persona-Augmented Emotional Support Conversation Generation

TL;DR

This paper introduces PAL, a framework that models seekers' personas to generate personalized emotional support in conversations, demonstrating improved performance over existing methods.

Contribution

It proposes a novel approach to infer and incorporate seekers' personas into dialogue models for emotional support, enhancing personalization and effectiveness.

Findings

PAL achieves state-of-the-art results on benchmark datasets.

Persona modeling significantly improves emotional support quality.

The approach outperforms baseline models in automatic and manual evaluations.

Abstract

Due to the lack of human resources for mental health support, there is an increasing demand for employing conversational agents for support. Recent work has demonstrated the effectiveness of dialogue models in providing emotional support. As previous studies have demonstrated that seekers' persona is an important factor for effective support, we investigate whether there are benefits to modeling such information in dialogue models for support. In this paper, our empirical analysis verifies that persona has an important impact on emotional support. Therefore, we propose a framework for dynamically inferring and modeling seekers' persona. We first train a model for inferring the seeker's persona from the conversation history. Accordingly, we propose PAL, a model that leverages persona information and, in conjunction with our strategy-based controllable generation method, provides personalized emotional support. Automatic and manual evaluations demonstrate that PAL achieves state-of-the-art results, outperforming the baselines on the studied benchmark. Our code and data are publicly available at https://github.com/chengjl19/PAL.