Global information enhancement and subgraph-level weakly contrastive learning for lightweight weakly supervised document-level event extraction

Guanqiu Qin, Nankai Lin, Menglan Shen, Qifeng Bai, Dong Zhou, Aimin Yang

Abstract: Highlights•We propose an approach for cross-sentence event extraction.•Our method injects context information with low extra computational costs.•The lightweight model has superior performance in the ChFinAnn dataset.•Our method shows a degree of flexibility when dealing with imbalanced data.•Our method has the potential to be implemented in tasks based on a graph network.