Improving Cascade Decoding with Syntax-aware Aggregator and Contrastive Learning for Event Extraction

Cascade decoding framework has shown superior performance on event extraction tasks. However, it treats a sentence as a sequence and neglects the potential benefits of the syntactic structure of sentences. In this paper, we improve cascade decoding with a novel module and a self-supervised task. Specifically, we propose a syntax-aware aggregator module to model the syntax of a sentence based on cascade decoding framework such that it captures event dependencies as well as syntactic information. Moreover, we design a type discrimination task to learn better syntactic representations of different event types, which could further boost the performance of event extraction. Experimental results on two widely used event extraction datasets demonstrate that our method could improve the original cascade decoding framework by up to 2.2% percentage points of F1 score and outperform a number of competitive baseline methods.