首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于概念图谱与BiGRU-Att模型的突发事件演化关系抽取
作者姓名:余蓓  刘宇  顾进广
作者单位:1.武汉科技大学计算机科学与技术学院,湖北 武汉,430065;2.武汉科技大学智能信息处理与实时工业系统湖北省重点实验室, 湖北 武汉,430065;3.武汉科技大学大数据科学与工程研究院,湖北 武汉,430065,1.武汉科技大学计算机科学与技术学院,湖北 武汉,430065;2.武汉科技大学智能信息处理与实时工业系统湖北省重点实验室, 湖北 武汉,430065;3.武汉科技大学大数据科学与工程研究院,湖北 武汉,430065,1.武汉科技大学计算机科学与技术学院,湖北 武汉,430065;2.武汉科技大学智能信息处理与实时工业系统湖北省重点实验室, 湖北 武汉,430065;3.武汉科技大学大数据科学与工程研究院,湖北 武汉,430065
基金项目:国家自然科学基金资助项目(U1836118,61673304);国家社会科学基金重大计划项目(11&ZD189);教育部高校产学研创新基金——新一代信息技术创新项目(2018A03025).
摘    要:针对现有突发事件演化关系抽取方法仅利用了句子本身的信息而忽略了背景知识的问题,引入概念图谱进行特征拓展,以获得更多的语义信息来改善演化关系抽取效果。首先根据概念图谱构建突发事件语义网络,通过特征迭代选择算法获得演化因子的概念特征,然后联合概念特征与突发事件文本作为双向门控循环单元(BiGRU)模型的输入进行特征学习,并利用注意力(Attention)机制对输出的特征信息序列实施加权变换,最后将学习到的特征序列输入到分类器进行演化关系分类。实验结果表明,所提出的基于概念图谱与BiGRU-Att模型的方法相比于现有方法,在准确率、召回率和F_1值等评价指标上均有提升。

关 键 词:关系抽取  突发事件  演化关系  概念图谱  双向门控循环单元  注意力机制
收稿时间:2019/12/17 0:00:00

Evolution relationship extraction of emergency based on concept graph and BiGRU-Att model
Authors:Yu Bei  Liu Yu and Gu Jinguang
Institution:1. College of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, China;2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, Wuhan 430065, China;3. Big Data Science and Engineering Research Institute, Wuhan University of Science and Technology, Wuhan 430065, China,1. College of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, China;2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, Wuhan 430065, China;3. Big Data Science and Engineering Research Institute, Wuhan University of Science and Technology, Wuhan 430065, China and 1. College of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, China;2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, Wuhan 430065, China;3. Big Data Science and Engineering Research Institute, Wuhan University of Science and Technology, Wuhan 430065, China
Abstract:To solve the problem that the existing methods for evolution relationship extraction of emergency only use the context of the sentences but ignore the background knowledge, this study introduces concept graph to expand the semantic features, so as to obtain more semantic information and improve the performance of evolution relationship classification. Firstly, an emergency semantic network is built based on concept graph, and concept features of the evolution factors are chosen by an iterative scheme. Secondly, the concept features combined with the emergency text are input to the bidirectional gated recurrent unit (BiGRU) model for feature learning, and the attention mechanism is used to transform the weight of the output feature sequence. Finally, the feature sequence is input to a classifier for evolution relationship classification. The experimental results show that, to judge by such evaluation indexes as precision, recall and F1-score, the proposed method based on concept graph and BiGRU-Att model is superior to the existing ones.
Keywords:relationship extraction  emergency  evolution relationship  concept graph  BiGRU  attention mechanism
本文献已被 CNKI 等数据库收录!
点击此处可从《》浏览原始摘要信息
点击此处可从《》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号