一种无结构金融公告多元关系抽取方法  

Multiple Relationship Extraction from Unstructured Financial Announcements

作　　者：周映彤 孟剑 郭岩[1] 刘悦[1] 贺广福 董琳 程学旗[1] ZHOU Yinɡtonɡ;MENG Jian;GUO Yan;LIU Yue;HE Guanɡfu;DONG Lin;CHENG Xueqi(Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;National Computer Network Emergency Response Technical Team/Coordination Center of China,Beijing 100029,China)

机构地区：[1]中国科学院计算技术研究所网络数据科学与技术实验室,北京100190 [2]国家计算机网络应急技术处理协调中心,北京100029

出　　处：《中文信息学报》2022年第2期76-84,共9页Journal of Chinese Information Processing

基　　金：国家重点研发计划(2017YFB0803302);国家自然科学基金(61802370)。

摘　　要：金融公告信息披露了企业运营的关键数据,具有应用价值。无结构金融公告中涉及复杂的财务关系,即多元关系。该文设计了基于依存分析树和频繁子图挖掘的垂直域多元关系抽取方法TextMining,可大大降低对数据集的依赖。进一步,受图卷积神经网络启发,该文设计了垂直域优化的FTA-GCN算法。在构建的适用金融公告数据集上,算法较强地关注以金融公告中常见的名词实体为核心的多元关系抽取,实验结果表明,算法具有良好的抽取效果。The financial announcement information discloses the key data of the company’s operation, involving complex financial relationships, namely multiple relationships. This paper designs TextMining, a vertical domain multivariate relationship extraction method based on dependency tree and frequent subgraph mining. Furthermore, inspired by the graph convolutional neural network, the FTA-GCN algorithm for vertical domain optimization is designed. In financial announcement dataset constructed in this paper, the algorithm can capture the multiple relationships between the common entities. Indicating that the algorithm has a good extraction performance.

关 键 词：金融公告 关系抽取 图卷积 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]