基于加权语义网的专家知识发现及表示方法  

Expert Knowledge Discovery and Representation Based on Weighted Semantic Network

作　　者：廖开际[1] 叶东海[1] 闫健峻[1] 吴敏[1] 

机构地区：[1]华南理工大学知识管理与企业信息化研究中心,广州510640

出　　处：《情报学报》2012年第1期60-64,共5页Journal of the China Society for Scientific and Technical Information

基　　金：国家自然科学基金项目（70871043,70801028）,教育部人文社会科学研究项目（08JC630027）.

摘　　要：在分析传统的以词形为切入点来建立知识内在关联的基础上，从语义网络的角度对专家知识发现及表示方法进行了研究。在语义关系建模时，综合考虑知识元的语义关系及其在文本中的重要性，提出了知识加权语义网（WSNK），从而实现专家知识的准确获取和表示。该方法可通过网络图表示专家知识的构成、通过语义描述专家知识领域等，具有客观、准确、易于理解等特点。最后结合一个实例对方法进行了验证和分析，结果表明，该方法能够客观、准确地理解和表示专家的知识。Based on the analysis of knowledge interconnectedness established by the word form method, this paper researches the discovery and representation of an expert＇ s knowledge from the view of semantic network. In the semantic relations modeling, both the semantic relation and importance of knowledge elements are considered. A knowledge weighted semantic network is presented which can discovery and represent expert knowledge accurately. Thus, the knowledge structure of an expert can be showed as a network and the filed knowledge can be described through semantic meaning more objective, accurate and easier to understand. A case study is given in the end. The result proves that this method can accurately understand and represent the expert knowledge.

关 键 词：加权语义网 知识元 语义关系 专家知识 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]