Exploiting Emotion-Semantic Correlations for Empathetic Response Generation

arXiv (Cornell University)

Abstract

Empathetic response generation aims to generate empathetic responses by understanding the speaker's emotional feelings from the language of dialogue. Recent methods capture emotional words in the language of communicators and construct them as static vectors to perceive nuanced emotions. However, linguistic research has shown that emotional words in language are dynamic and have correlations with other grammar semantic roles, i.e., words with semantic meanings, in grammar. Previous methods overlook these two characteristics, which easily lead to misunderstandings of emotions and neglect of key semantics. To address this issue, we propose a dynamical Emotion-Semantic Correlation Model (ESCM) for empathetic dialogue generation tasks. ESCM constructs dynamic emotion-semantic vectors through the interaction of context and emotions. We introduce dependency trees to reflect the correlations between emotions and semantics. Based on dynamic emotion-semantic vectors and dependency trees, we propose a dynamic correlation graph convolutional network to guide the model in learning context meanings in dialogue and generating empathetic responses. Experimental results on the EMPATHETIC-DIALOGUES dataset show that ESCM understands semantics and emotions more accurately and expresses fluent and informative empathetic responses. Our analysis results also indicate that the correlations between emotions and semantics are frequently used in dialogues, which is of great significance for empathetic perception and expression.

Authors 9

1. Zhou Yang

   Fuzhou University

   Affiliation as printed

   College of Computer and Data Science , Fuzhou University ;

   Digital Fujian Institute of Financial Big Data , Fuzhou , China

2. Zhaochun Ren Aachen

   Leiden University

   Affiliation as printed

   Leiden University , Leiden , The Netherlands

3. Yufeng Wang

   Fuzhou University

   Affiliation as printed

   College of Computer and Data Science , Fuzhou University ;

   Digital Fujian Institute of Financial Big Data , Fuzhou , China

4. Xiaofei Zhu

   Chongqing University of Technology

   Affiliation as printed

   College of Computer Science and Technology , Chongqing University of Technology , Chongqing , China {200310007 , 211027083 , n180320046 , 210310002 , 221010003

5. Zhihao Chen

   Fuzhou University

   Affiliation as printed

   College of Computer and Data Science , Fuzhou University ;

   Digital Fujian Institute of Financial Big Data , Fuzhou , China

6. Yunbing Wu

   Fuzhou University

   Affiliation as printed

   College of Computer and Data Science , Fuzhou University ;

   Digital Fujian Institute of Financial Big Data , Fuzhou , China

7. Yisong Su

   Fuzhou University

   Affiliation as printed

   College of Computer and Data Science , Fuzhou University ;

   Digital Fujian Institute of Financial Big Data , Fuzhou , China

8. Sibo Ju

   Fuzhou University

   Affiliation as printed

   College of Computer and Data Science , Fuzhou University ;

   Digital Fujian Institute of Financial Big Data , Fuzhou , China

9. Xiangwen Liao

   Fuzhou University

   Affiliation as printed

   College of Computer and Data Science , Fuzhou University ;

   Digital Fujian Institute of Financial Big Data , Fuzhou , China