Persona Extraction Through Semantic Similarity for Emotional Support Conversation Generation
This addresses the challenge of obtaining user personas in emotional support systems, offering a novel method for persona extraction, though it is incremental in building on prior persona-based approaches.
The paper tackles the problem of automatically inferring user personas from dialogues for emotional support conversation generation, proposing the PESS framework with completeness and consistency losses based on semantic similarity, and shows it effectively generates supportive responses.
Providing emotional support through dialogue systems is becoming increasingly important in today's world, as it can support both mental health and social interactions in many conversation scenarios. Previous works have shown that using persona is effective for generating empathetic and supportive responses. They have often relied on pre-provided persona rather than inferring them during conversations. However, it is not always possible to obtain a user persona before the conversation begins. To address this challenge, we propose PESS (Persona Extraction through Semantic Similarity), a novel framework that can automatically infer informative and consistent persona from dialogues. We devise completeness loss and consistency loss based on semantic similarity scores. The completeness loss encourages the model to generate missing persona information, and the consistency loss guides the model to distinguish between consistent and inconsistent persona. Our experimental results demonstrate that high-quality persona information inferred by PESS is effective in generating emotionally supportive responses.