Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization
Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization
复制标题
DOI：
10.48550/arxiv.2305.18926
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Xinyu Wang;Lin Gui;Yulan He
中科院分区：
文献类型：
--
作者：
Xinyu Wang;Lin Gui;Yulan He
文档级多事件抽取的目的是从给定文档中自动抽取结构信息。最新的方法通常包括两个步骤：（1）建模实体交互;（2）将实体交互解码为事件。然而，这样的方法忽略了多个事件的相互依赖性的全局视图。此外，事件通过迭代地合并其相关实体作为参数来解码，这可能遭受错误传播并且计算效率低下。在本文中，我们提出了一种替代方法，用于文档级多事件提取事件代理节点和Hausdorff距离最小化。代表伪事件的事件代理节点能够与其他事件代理节点建立连接，基本上捕获全局信息。Hausdorff距离使得可以比较预测事件集和地面实况事件集之间的相似性。通过直接最小化Hausdorff距离，直接向全局最优值训练模型，从而提高性能并减少训练时间。实验结果表明，我们的模型在两个数据集上的F1得分方面优于以前的最先进的方法，而训练时间只有一小部分。
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.