Document-Level Event Argument Extraction by Leveraging Redundant Information and Closed Boundary Loss

Anonymous

Abstract: In document-level event argument extraction, an argument is likely to appear multiple times in different expressions in the document. The redundancy of arguments underlying multiple sentences is beneficial but is often overlooked. In addition, in event argument extraction, the majority entities are regarded as class “others", i.e. universum class, which is composed of heterogeneous entities without typical common features. Classifiers trained by cross entropy loss could easily misclassify universum class because of their open decision boundary. In this paper, to make use of redundant information underlying a document, we build an entity coreference graph with graph2token module to produce comprehensive and coreference-aware representation for every entity, and then build an entity summary graph to merge the multiple extraction results. To better classify universum class, we propose a new loss function to build classifiers with closed boundaries. Experimental results show that our model outperforms the previous state-of-the-art models by 3.35% in F1-score.

Paper Type: long