基于形式概念分析的学科术语层次关系构建研究  

Study on Construction of Hierarchy Relationship of Subject Terms Based on Formal Concept Analysis

作　　者：王昊[1] 朱惠[1] 邓三鸿[2] 

机构地区：[1]南京大学信息管理学院,南京210023 [2]南京大学江苏省数据工程与知识服务重点实验室,南京210023

出　　处：《情报学报》2015年第6期616-627,共12页Journal of the China Society for Scientific and Technical Information

基　　金：国家社科重大招标项目“面向学科领域的网络信息资源深度聚合与服务研究”(12&ZD221);江苏省自然科学基金项目“面向专利预警的中文本体学习研究”(BK20130587)等的资助

摘　　要：本体是领域知识的有效组织和描述，本体学习则是实现本体自动构建的方法体系和技术集合。本文以本体学习理论为指导，提出了一种以文档一术语空间为核心、形式概念分析（FCA）为手段的中文领域本体层次结构自动构建的有效方法，并以“白血病”领域为例，对面向学科资源的医学专业术语层次关联的抽取进行了详细论证，具体包括专业术语的抽取和筛选，术语文档关联的修正等数据清洗过程；文档术语矩阵的建立，领域概念格的自动生成，以及概念格中术语属性的层次关联建立等FCA过程；术语层次关联的自动OWL描述和存储，和领域本体的概念检索和可视化展示过程等。Ontology is the effective organization and description for domain knowledge and Ontology Learning （OL） is the methodology and technology to construct Ontology automatically. With the OL theory as a guide, this paper proposes an effective method, which is with documents-terms space as a core and with Formal Concept Analysis （FCA） as a means, to construct hierarchy structure of Chinese Domain Ontology automatically. Taking ＂leukemia＂ field for an example, it in detail demonstrates the extracting process on hierarchy relationship of Medical professional terms oriented disciplines resource, which specifically contains 3 processes. First is the data clearing process as initialization including extracting and filtering of professional terms, and amendment of association of terms from documents. Second is the FCA process including building of documents-terms matrix, automatic generation of domain concept lattice and construction of hierarchy relationship of properties from terms in concept lattice. Third is the terms ontology description process including automatic OWL description and storage of hierarchy associations of terms, concept searching and visually displaying of domain ontology.

关 键 词：学科术语 层次关系 本体学习 形式概念分析 概念格OWL 

分 类 号：G254[文化科学—图书馆学]