Knowledge-Enhanced Self-Supervised Prototypical Network for Few-Shot Event Detection
Kailin Zhao, Xiaolong Jin, Long Bai, Jiafeng Guo, Xueqi Cheng · 2022
Prototypical network based joint methods have attracted much attention in few-shot event detection, which carry out event detection in a unified sequence tagging framework.However, these methods suffer from the inaccurate prototype representation problem, due to two main reasons: the number of instances for calculating prototypes is limited; And, they do not well capture the relationships among event prototypes.To deal with this problem, we propose a Knowledge-Enhanced self-supervised Prototypical Network, called KE-PN, for few-shot event detection.KE-PN adopts hybrid rules, which can automatically align event types to an external knowledge base, i.e., FrameNet, to obtain more instances.It proposes a selfsupervised learning method to filter out noisy data from enhanced instances.KE-PN is further equipped with an auxiliary event type relationship classification module, which injects the relationship information into representations of event prototypes.Extensive experiments on three benchmark datasets, i.e., Few-Event, MAVEN, and ACE2005 demonstrate the state-of-the-art performance of KE-PN.