PAL：融入用户画像的情感支持对话生成
PAL: Persona-Augmented Emotional Support Conversation Generation
AI总结：
本文提出 PAL 框架，通过从对话历史动态推断求助者画像并结合基于策略的可控生成，实现个性化情感支持，在基准上取得最优效果。
摘要：
由于心理健康支持领域人力资源不足，使用对话智能体提供支持的需求日益增长。近期研究已证明对话模型在提供情感支持方面的有效性。鉴于先前研究表明求助者的用户画像（persona）是实现有效支持的重要因素，我们探究在支持型对话模型中建模此类信息是否具有益处。本文的实证分析验证了用户画像对情感支持具有重要影响。因此，我们提出一个动态推断并建模求助者用户画像的框架。我们首先训练一个模型，从对话历史中推断求助者的用户画像。在此基础上，我们提出 PAL 模型，该模型利用用户画像信息，并结合我们基于策略的可控生成方法，提供个性化的情感支持。自动评估和人工评估均表明，PAL 取得了当前最优结果，在所研究的基准上优于基线模型。我们的代码和数据已在 https://github.com/chengjl19/PAL 公开。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
