Joint Event Extraction Based on Skip-Window Convolutional Neural Networks

Traditional approaches to the task of ACE event extraction are either the joint model with elaborately designed features which may lead to generalization and data-sparsity problems, or the word-embedding model based on a twostage, multi-class classification architecture, which suffers from error propagation since event triggers and arguments are predicted in isolation. This paper proposes a novel event-extraction method that not only extracts triggers and arguments simultaneously, but also adopts a framework based on convolutional neural networks (CNNs) to extract features automatically. However, CNNs can only capture sentence-level features, so we propose the skip-window convolution neural networks (S-CNNs) to extract global structured features, which effectively capture the global dependencies of every token in the sentence. The experimental results show that our approach outperforms other state-of-the-art methods.