从隐式用户反馈、情绪和人口统计信息中学习：面向任务型与文档基础对话
Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues
AI总结：
本文提出FEDI数据集，首个标注隐式用户反馈、情绪和人口统计信息的英文任务导向与文档基础对话数据集，实验证明这些信息显著提升任务完成度和事实一致性。
摘要：
隐式用户反馈、用户情绪和人口统计信息已被证明是提高对话系统生成响应的准确性和用户参与度的有前景的信息来源。然而，此类信息对任务完成度和事实一致性（任务导向型对话和文档基础对话的重要评判标准）的影响尚不明确。为解决这一问题，我们引入了FEDI，这是首个标注了此类信息的英文任务导向型与文档基础对话数据集。我们使用Flan-T5、GPT-2和Llama 2进行的实验表明，这些信息对任务完成度和事实一致性有特别积极的影响。我们的人类评估参与者报告称，由反馈训练模型生成的响应更具信息量（Flan-T5和GPT-2）、相关性和事实一致性（Llama 2）。
英文摘要：
Implicit user feedback, user emotions and demographic information have shown to be promising sources for improving the accuracy and user engagement of responses generated by dialogue systems. However, the influence of such information on task completion and factual consistency, which are important criteria for task-oriented and document-grounded dialogues, is not yet known. To address this, we introduce FEDI, the first English task-oriented and document-grounded dialogue dataset annotated with this information. Our experiments with Flan-T5, GPT-2 and Llama 2 show a particularly positive impact on task completion and factual consistency. Participants in our human evaluation reported that the responses generated by the feedback-trained models were more informative (Flan-T5 and GPT-2), relevant and factual consistent (Llama 2).
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。
