DuEE1.0.zip

Considering that the traditional deep learning event extraction method ignores the correlation between word features and sequence information, it cannot fully explore the hidden associations between events and events and between events and primary attributes. To solve these problems, we developed a new framework for event extraction called the masked attention-guided dynamic graph aggregation network.

鉴于传统深度学习事件抽取方法忽视了词特征与序列信息之间的关联，无法充分挖掘事件间以及事件与核心属性间的隐藏关联。针对上述问题，我们研发了一款全新的事件抽取框架——掩码注意力引导动态图聚合网络（masked attention-guided dynamic graph aggregation network）。

搜集汇总

背景与挑战

背景概述

DuEE1.0.zip是一个自然语言处理领域的事件提取算法数据集，大小为5.54 MB，发布于2024年10月23日，采用CC BY 4.0许可。