Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations

TL;DR

This paper introduces a novel knowledge-enhanced framework for mixed-initiative emotional support conversations, enabling proactive assistance and improved dialogue quality through large-scale mental health knowledge integration.

Contribution

It presents a new analysis schema, proposes four evaluation metrics, and develops KEMI, a framework that retrieves case knowledge for more effective emotional support dialogues.

Findings

KEMI outperforms baselines in content preservation

Effective retrieval of mental health knowledge improves dialogue quality

Analysis highlights the importance of mixed-initiative strategies in ESC

Abstract

Unlike empathetic dialogues, the system in emotional support conversations (ESC) is expected to not only convey empathy for comforting the help-seeker, but also proactively assist in exploring and addressing their problems during the conversation. In this work, we study the problem of mixed-initiative ESC where the user and system can both take the initiative in leading the conversation. Specifically, we conduct a novel analysis on mixed-initiative ESC systems with a tailor-designed schema that divides utterances into different types with speaker roles and initiative types. Four emotional support metrics are proposed to evaluate the mixed-initiative interactions. The analysis reveals the necessity and challenges of building mixed-initiative ESC systems. In the light of this, we propose a knowledge-enhanced mixed-initiative framework (KEMI) for ESC, which retrieves actual case knowledge from a large-scale mental health knowledge graph for generating mixed-initiative responses. Experimental results on two ESC datasets show the superiority of KEMI in both content-preserving evaluation and mixed initiative related analyses.