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.

翻译：通过对话系统提供情感支持在当今世界正变得越来越重要，因为这可以在许多对话场景中支持心理健康和社交互动。已有研究表明，使用角色信息对于生成共情和支持性回应是有效的。这些工作通常依赖预先提供的角色信息，而非在对话过程中推断角色。然而，在对话开始前获取用户角色信息并不总是可行的。为了解决这一挑战，我们提出了PESS（基于语义相似度的角色信息提取），这是一个新颖的框架，能够自动从对话中推断出信息丰富且一致的角色信息。我们基于语义相似度分数设计了完整性损失和一致性损失。完整性损失鼓励模型生成缺失的角色信息，而一致性损失则引导模型区分一致和不一致的角色信息。实验结果表明，PESS推断出的高质量角色信息能有效生成情感支持性回应。