Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations
This addresses the challenge of building proactive emotional support systems for mental health applications, though it appears incremental as it builds on existing ESC methods with a novel mixed-initiative focus.
The paper tackles the problem of mixed-initiative emotional support conversations, where both user and system can lead, by proposing a knowledge-enhanced framework (KEMI) that retrieves case knowledge from a mental health graph to generate responses, achieving superior results on two datasets in content-preserving and mixed-initiative evaluations.
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.