Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization
This addresses the problem of extracting multiple events from documents for natural language processing applications, offering a novel method with improved performance and efficiency.
The paper tackled document-level multi-event extraction by proposing an approach with event proxy nodes and Hausdorff distance minimization to capture global event interdependencies and improve efficiency, resulting in outperforming previous state-of-the-art methods in F1-score on two datasets with reduced training time.
Document-level multi-event extraction aims to extract the structural information from a given document automatically. Most recent approaches usually involve two steps: (1) modeling entity interactions; (2) decoding entity interactions into events. However, such approaches ignore a global view of inter-dependency of multiple events. Moreover, an event is decoded by iteratively merging its related entities as arguments, which might suffer from error propagation and is computationally inefficient. In this paper, we propose an alternative approach for document-level multi-event extraction with event proxy nodes and Hausdorff distance minimization. The event proxy nodes, representing pseudo-events, are able to build connections with other event proxy nodes, essentially capturing global information. The Hausdorff distance makes it possible to compare the similarity between the set of predicted events and the set of ground-truth events. By directly minimizing Hausdorff distance, the model is trained towards the global optimum directly, which improves performance and reduces training time. Experimental results show that our model outperforms previous state-of-the-art method in F1-score on two datasets with only a fraction of training time.