Improving Representation With Intra- and Inter-Clause Commonsense Injection for Emotion-Cause Pair Extraction

Emotion-Cause Pair Extraction (ECPE) aims to simultaneously extract emotions and their corresponding causes, which is crucial for understanding human intent. Generally, machines can extract or infer emotion causes by incorporating commonsense knowledge with document contexts. However, most existing works lack integration of commonsense knowledge when analyzing human emotions and their triggering causes. To address this issue, this paper introduces a commonsense knowledge-injection framework (CokECPE), designed to enhance representation learning and thereby improve model performance. CokECPE enriches representation learning by incorporating commonsense knowledge at intra-clause and inter-clause levels. First, CokECPE retrieves concept-level and event-level knowledge from the commonsense conversational knowledge graph <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\text{C}^{3}\text{KG}$</tex-math></inline-formula> . Next, it injects these commonsense features into a pretrained model, fusing them with multilevel textual information. Finally, CokECPE establishes dependencies between clauses based on commonsense reasoning, selecting the paths most similar to the emotion-cause pair candidates as edges, effectively embedding commonsense relations into the representation learning process. Experimental results on two public datasets demonstrate that CokECPE consistently outperforms existing methods, achieving enhanced state-of-the-art performance and validating its effectiveness.