Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction
This work improves emotion-cause pair extraction for natural language processing applications, but it is incremental as it builds on existing methods by enhancing feature interaction.
The paper tackles the problem of emotion-cause pair extraction (ECPE) by addressing the imbalance in inter-task feature interaction in previous sequential methods, proposing a Pair-Based Joint Encoding (PBJE) network that simultaneously generates pairs and clauses features, achieving state-of-the-art performance on a Chinese benchmark corpus.
Emotion-cause pair extraction (ECPE) aims to extract emotion clauses and corresponding cause clauses, which have recently received growing attention. Previous methods sequentially encode features with a specified order. They first encode the emotion and cause features for clause extraction and then combine them for pair extraction. This lead to an imbalance in inter-task feature interaction where features extracted later have no direct contact with the former. To address this issue, we propose a novel Pair-Based Joint Encoding (PBJE) network, which generates pairs and clauses features simultaneously in a joint feature encoding manner to model the causal relationship in clauses. PBJE can balance the information flow among emotion clauses, cause clauses and pairs. From a multi-relational perspective, we construct a heterogeneous undirected graph and apply the Relational Graph Convolutional Network (RGCN) to capture the various relationship between clauses and the relationship between pairs and clauses. Experimental results show that PBJE achieves state-of-the-art performance on the Chinese benchmark corpus.