Improving shared argument identification in Japanese event relation knowledge acquisition

Abstract

Event relation knowledge represents the knowledge of causal and temporal relations between events. Shared arguments of event relation knowledge encode patterns of role shifting in successive events. A two-stage framework was proposed for the task of Japanese event relation knowledge acquisition, in which related event pairs are first extracted, and shared arguments are then identified to form the complete event relation knowledge. This paper focuses on the second stage of this framework, and proposes a method to improve the shared argument identification of related event pairs. We constructed a gold dataset for shared argument learning. By evaluating our system on this gold dataset, we found that our proposed model outperformed the baseline models by a large margin.