Revisiting Event Argument Extraction: Can EAE Models Learn Better When Being Aware of Event Co-occurrences?

Event co-occurrences have been proved effective for event extraction (EE) in previous studies, but have not been considered for event argument extraction (EAE) recently. In this paper, we try to fill this gap between EE research and EAE research, by highlighting the question that "Can EAE models learn better when being aware of event co-occurrences?". To answer this question, we reformulate EAE as a problem of table generation and extend a SOTA prompt-based EAE model into a nonautoregressive generation framework, called TabEAE, which is able to extract the arguments of multiple events in parallel. Under this framework, we experiment with 3 different training-inference schemes on 4 datasets (ACE05, RAMS, WikiEvents and MLEE) and discover that via training the model to extract all events in parallel, it can better distinguish Figure 1: An illustration of EE and EAE. The triggers the semantic boundary of each event are in red and the arguments are underlined. EE models and its ability to extract single event gets aim at extracting all events concurrently, whereas mainstream substantially improved. Experimental results EAE models are trained to extract the arguments show that our method achieves new state-ofthe-art for one event trigger at a time.