Guimin Hu, Zhihong Zhu, Daniel Hershcovich, Lijie Hu, Hasti Seifi, Jiayuan Xie. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
13 March 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Emotion-cause pair extraction (ECPE) task aims to extract all the pairs of emotions and their causes from an unannotated emotion text. The previous works usually extract the emotion-cause pairs from two perspectives of emotion and cause. However, emotion extraction is more crucial to the ECPE task than cause extraction. Motivated by this analysis, we propose an end-to-end emotion-cause extraction approach oriented toward emotion prediction (EPO-ECPE), aiming to fully exploit the potential of emotion prediction to enhance emotion-cause pair extraction. Considering the strong dependence between emotion prediction and emotion-cause pair extraction, we propose a synchronization mechanism to share their improvement in the training process. That is, the improvement of emotion prediction can facilitate the emotion-cause pair extraction, and then the results of emotion-cause pair extraction can also be used to improve the accuracy of emotion prediction simultaneously. For the emotion-cause pair extraction, we divide it into genuine pair supervision and fake pair supervision, where the genuine pair supervision learns from the pairs with more possibility to be emotion-cause pairs. In contrast, fake pair supervision learns from other pairs. In this way, the emotion-cause pairs can be extracted directly from the genuine pair, thereby reducing the difficulty of extraction. Experimental results show that our approach outperforms the 13 compared systems and achieves new state-of-the-art performance.
29 April 2024 in IEEE Transactions on Affective Computing
Emotion-cause pair extraction (ECPE) aims to extract emotions and their corresponding cause from a document. The previous works have made great progress. However, there exist two major issues in existing works. First, most existing works mainly focus on the semantic relation between the emotion clause and cause clause, ignoring their inner statistical relation in representation space. Second, the existing works are sensitive to the relative position between the emotion clause and cause clause, which damages the model's robustness. To address the two issues, we propose a hierarchical contrastive learning framework (HCL-ECPE), which hierarchically performs contrastive learning on representation from two levels. The first level is inter-clause contrastive learning (ICCL), which performs between emotion clause and cause clause through mutual information maximization. The second level is intra-pair contrastive learning (IPCL), which performs between clause representation and pair representation through contrastive predictive coding (CPC). HCL-ECPE integrates ICCL and IPCL modules to explore the statistical relations between the emotion clause, cause clause, and their constructed emotion-cause pair from the perspective of mutual information, thereby improving the model performance and robustness. Experimental results on two public datasets, ECPED and RECCON, demonstrate that HCL-ECPE outperforms the most competitive baselines. Furthermore, ICCL and IPCL are orthogonal to the existing model, and introducing them into the current models updates state-of-the-art performance.
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 $\text{C}^{3}\text{KG}$ . 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.