K-ESConv: 基于提示学习的情感支持对话系统知识注入方法
K-ESConv: Knowledge Injection for Emotional Support Dialogue Systems via Prompt Learning
AI总结：
针对自动心理咨询需大量专业知识的需求，提出基于提示学习的知识注入方法K-ESConv，将论坛情感知识融入回复生成，在ESConv数据集上评估显示其效果优于基线，提升回复质量。
摘要：
自动心理咨询需要大量可在在线咨询论坛中获取的专业知识。受此启发，我们提出K-ESConv，这是一种用于情感支持对话系统的新型基于提示学习的知识注入方法，可将论坛知识迁移到回复生成任务中。我们在情感支持数据集ESConv上评估该模型，模型会从外部专业情感问答论坛检索并整合知识。实验结果表明，该方法在自动评估和人工评估上均优于现有基线，显著提升了回复的相关性与多样性，能为求助者提供更多安慰和更好的建议。
英文摘要：
Automatic psychological counseling requires mass of professional knowledge that can be found in online counseling forums. Motivated by this, we propose K-ESConv, a novel prompt learning based knowledge injection method for emotional support dialogue system, transferring forum knowledge to response generation. We evaluate our model on an emotional support dataset ESConv, where the model retrieves and incorporates knowledge from external professional emotional Q\&A forum. Experiment results show that the proposed method outperforms existing baselines on both automatic evaluation and human evaluation, which shows that our approach significantly improves the correlation and diversity of responses and provides more comfort and better suggestion for the seeker.
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。
