Exploiting Emotion-Semantic Correlations for Empathetic Response Generation
This work addresses the challenge of empathetic response generation for dialogue systems by incorporating linguistic insights, though it appears incremental as it builds on existing methods with a focus on dynamic correlations.
The paper tackles the problem of generating empathetic responses by modeling dynamic correlations between emotional words and semantic roles in dialogue, proposing the Emotion-Semantic Correlation Model (ESCM) which uses dependency trees and a graph convolutional network to improve accuracy and fluency on the EMPATHETIC-DIALOGUES dataset.
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.