Chen Yubo, Zhou Tong, Li Sirui, Zhao Jun
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China.
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 101408, China.
Sci Data. 2025 May 10;12(1):772. doi: 10.1038/s41597-025-05083-9.
Financial event modeling is fundamental to financial investment decisions and risk management, crucial for the stability and growth of financial institutions, and helps ensure the stability and quality of people's lives. Utilizing state-of-the-art natural language processing techniques for automated financial event extraction addresses the inefficiencies and high costs associated with traditional event identification and modeling, which rely heavily on financial domain experts. However, existing datasets fail to tackle the issues with long documents in practical situations. To address this, we first propose DocFEE, a large-scale Document-level Chinese Financial Event Extraction dataset. It reflects the length of announcement documents and the long-distance dependencies of event arguments in real-world scenarios.
金融事件建模是金融投资决策和风险管理的基础，对金融机构的稳定和发展至关重要，并有助于确保人们生活的稳定和质量。利用最先进的自然语言处理技术进行自动金融事件提取，解决了与传统事件识别和建模相关的效率低下和成本高昂的问题，传统方法严重依赖金融领域专家。然而，现有数据集未能解决实际情况下长文档的问题。为了解决这个问题，我们首先提出了DocFEE，一个大规模的文档级中文金融事件提取数据集。它反映了公告文档的长度以及现实场景中事件论据的长距离依赖关系。
