面向领域概念的语义关系抽取方法  

An Automatic Semantic Relation Extraction Method for Domain Concepts

作　　者：王舒琪[1] 冯晓[2] 张树武[2] 关虎[2] WANG Shu-qi;FENG Xiao;ZHANG Shu-wu;GUAN Hu(Information engineering college,Communication University of China,Beijing 100024,China;Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]中国传媒大学信息工程学院,北京100024 [2]中国科学院自动化研究所数字内容中心,北京100190

出　　处：《中国传媒大学学报（自然科学版）》2017年第3期34-40,共7页Journal of Communication University of China：Science and Technology

基　　金：国家科技支撑计划课题"数字出版资源集成投送系统研发"(课题编号:2015BAH49F01)

摘　　要：提出了一个针对领域概念的开放式语义关系抽取方法,不需要预先定义关系类型,对句子进行依存句法分析,抽取最短依存路径,并通过添加启发式规则获取描述领域概念对的关系指示词。实验结果表明,所提出的方法是可行和有效的,能获得特定领域中存在的丰富的语义关系。An open semantic relation extraction method for domain concepts is presented,an method which does not need to define relation types in advance.First,analyze sentences based on Dependency Parsing(DP),and then extract The Shortest Dependency Path(TSDP)between domain concepts.Finally,obtain the relation words for domain concepts by adding the constraint rules.Experiments demonstrate that the proposed method is effective.It can obtain rich relationships in special domain.

关 键 词：领域概念 语义关系 依存句法分析 最短依存路径 关系指示词 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]