arXiv 2404.072292024-04-03cs.CLcs.AI

对话系统中受人格影响的情绪生成

Personality-affected Emotion Generation in Dialog Systems

The Hong Kong Polytechnic University（香港理工大学）；Lingnan University（岭南大学）；Tsinghua University（清华大学）

Zhiyuan Wen, Jiannong Cao, Jiaxing Shen, Ruosong Yang, Shuaiqi Liu, Maosong Sun

备注：: Accepted by ACM Transactions on Information Systems

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有对话系统情绪回复不一致的问题，提出受人格影响的情绪生成任务，构建标注数据集PELD，通过将人格建模为心境转换权重的方法，显著提升了情绪生成的宏F1和加权F1指标。

摘要：

为回复生成恰当的情绪是对话系统在各类应用场景中实现类人交互的关键。以往大多数对话系统试图通过从匿名对话数据中学习共情方式来实现这一目标，但这类方法生成的情绪回复可能存在不一致性，会降低用户参与度和服务质量。心理学研究表明，人类的情绪表达植根于人格特质。因此，我们提出了一项新任务——受人格影响的情绪生成（Personality-affected Emotion Generation），旨在根据赋予对话系统的人格生成情绪，并进一步通过受人格影响的心境转换探究解决方案。具体而言，我们首先构建了一个带有情绪和人格标注的日常对话数据集Personality EmotionLines Dataset（PELD）。随后，我们分析了该任务面临的挑战，即：（1）异质地整合人格与情绪因素；（2）在对话上下文中提取多粒度情绪信息。最后，我们提出通过在对话系统中模拟心境转换过程，将人格建模为转换权重，从而解决上述挑战。我们在PELD上开展了大量实验进行评估，结果表明，采用我们的方法后，情绪生成性能相较于BERT-base模型，宏F1值提升了13%，加权F1值提升了5%。

英文摘要：

Generating appropriate emotions for responses is essential for dialog systems to provide human-like interaction in various application scenarios. Most previous dialog systems tried to achieve this goal by learning empathetic manners from anonymous conversational data. However, emotional responses generated by those methods may be inconsistent, which will decrease user engagement and service quality. Psychological findings suggest that the emotional expressions of humans are rooted in personality traits. Therefore, we propose a new task, Personality-affected Emotion Generation, to generate emotion based on the personality given to the dialog system and further investigate a solution through the personality-affected mood transition. Specifically, we first construct a daily dialog dataset, Personality EmotionLines Dataset (PELD), with emotion and personality annotations. Subsequently, we analyze the challenges in this task, i.e., (1) heterogeneously integrating personality and emotional factors and (2) extracting multi-granularity emotional information in the dialog context. Finally, we propose to model the personality as the transition weight by simulating the mood transition process in the dialog system and solve the challenges above. We conduct extensive experiments on PELD for evaluation. Results suggest that by adopting our method, the emotion generation performance is improved by 13% in macro-F1 and 5% in weighted-F1 from the BERT-base model.

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。