Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (19): 148-157.DOI: 10.3778/j.issn.1002-8331.2306-0319

• Pattern Recognition and Artificial Intelligence • Previous Articles     Next Articles

Method for Generating Empathetic Responses by Integrating Emotional Intent and Emotional Cause

WANG Ningzhe, TANG Hong, ZHU Chuanrun, LIU Zhong   

  1. 1. School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
    2. Chongqing Key Lab of Mobile Communications Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Online:2024-10-01 Published:2024-09-30

融合情感意图和情感原因的共情回复生成方法

王宁喆,唐宏,朱传润,刘钟   

  1. 1. 重庆邮电大学  通信与信息工程学院,重庆  400065
    2. 重庆邮电大学  移动通信技术重庆市重点实验室,重庆  400065

Abstract: Empathetic dialogue is an important area of research in dialogue systems. However, current studies on empathetic dialogue tend to focus more on generating emotion-dependent responses, while overlooking the inclusion of emotional intent and emotional cause information during the dialogue process. This may result in overly generic or less empathetic responses, leading to a diminished user experience. To enhance the quality of empathetic response generation, a novel approach is proposed that integrates emotional intent and emotional cause. Firstly, the intent prediction module is employed to extract emotional intent information. Secondly, the emotional cause detection module is utilized to capture emotional cause information. Lastly, the response generation module incorporates intent embedding and emotion embedding, and introduces a gate mechanism for emotional cause and a copying mechanism. This enables dynamic selection of emotional cause and emotional intent information, facilitating the generation of empathetic responses that are relevant to the intent and emotionally appropriate. Experimental results on the EmpatheticDialogues dataset demonstrate significant improvements in both response diversity and empathetic quality achieved by the proposed method.

Key words: empathetic responses, emotional intent, emotional cause, gate mechanism, copy mechanism

摘要: 共情对话是对话系统研究中的一个重要领域,然而,现有的共情对话研究往往更关注情绪依赖的响应生成,却忽略对话过程中的情感意图信息和情感原因信息,这可能导致生成的共情回复过于通用化或共情性较低,从而降低用户的体验,为了提高共情回复生成的质量,提出了一种融合情感意图和情感原因的共情回复生成方法。通过意图预测模块提取情感意图信息。通过情感原因检测模块提取情感原因信息。在回复生成模块进行意图嵌入和情绪嵌入,并引入情感原因门控机制和复制机制,动态地选择情感原因信息和情感意图信息,促使模型生成与意图相关并且情感合适的共情回复。在EmpatheticDialogues数据集上的实验表明,该方法生成的回复在多样性和共情性方面得到了一定的提升。

关键词: 共情回复, 情感意图, 情感原因, 门控机制, 复制机制