Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailment

TL;DR

This paper introduces KBCIN, a novel model that leverages three types of commonsense knowledge to better understand conversational context and accurately identify causal utterances responsible for emotional expressions.

Contribution

The paper proposes a knowledge-bridged causal interaction network that effectively integrates multiple types of commonsense knowledge for causal emotion entailment in conversations.

Findings

KBCIN outperforms most baseline models in causal emotion entailment tasks.

The use of CSK as semantic and causal bridges improves contextual understanding.

Experimental results validate the effectiveness of the proposed knowledge integration approach.

Abstract

Causal Emotion Entailment aims to identify causal utterances that are responsible for the target utterance with a non-neutral emotion in conversations. Previous works are limited in thorough understanding of the conversational context and accurate reasoning of the emotion cause. To this end, we propose Knowledge-Bridged Causal Interaction Network (KBCIN) with commonsense knowledge (CSK) leveraged as three bridges. Specifically, we construct a conversational graph for each conversation and leverage the event-centered CSK as the semantics-level bridge (S-bridge) to capture the deep inter-utterance dependencies in the conversational context via the CSK-Enhanced Graph Attention module. Moreover, social-interaction CSK serves as emotion-level bridge (E-bridge) and action-level bridge (A-bridge) to connect candidate utterances with the target one, which provides explicit causal clues for the Emotional Interaction module and Actional Interaction module to reason the target emotion. Experimental results show that our model achieves better performance over most baseline models. Our source code is publicly available at https://github.com/circle-hit/KBCIN.