RCEAE: A Role Correlation-enhanced Model for Event Argument Extraction

Yiming Hei, Jiawei Sheng, Shu Guo, Lihong Wang, Qian Li, Jianwei Liu, Yizhong Liu, Prayag Tiwari

Abstract: Highlights•In this paper, we investigate two crucial correlations potentially benefiting to the event argument extraction task, namely intra- and inter-event role correlations.•The intra-event role correlations consider the role dependency within an event and the inter-event role correlations leverage the relevance among roles across events.•To take advantage of these correlations, we propose the RCEAE model based on event prompt templates and role label graphs.•We conduct experiments on three public datasets and demonstrate the advantages of RCEAE.