面向智能搜索引擎的本体学习研究

Study on ontology learning for intelligent search engine

智能搜索引擎是解决当前网络信息检索中存在诸多瓶颈问题的有效途径。智能搜索引擎需要获取、预处理、表示和集成不同层次的(如HTML/XML/RDF/OWL文档)的数据和信息,并最终转换成各领域的智能语义信息。领域本体是实行智能的关键。提出了一种实现从Web文档中(半)自动构建本体的学习系统框架,并讨论本体学习中概念的获取、相互关系的获取等关键问题。

Intelligent search engine is an effective tool for solving many bottleneck problems in network information retrieval. It involves acquiring, preprocessing, representing and integrating data and information available at different levels of services （such as HTML/XML/RDF/OWL etc） and eventually converts them into useful intelligent semantic information of each do- main. This paper proposed firstly a systemic framework for building （semi-） automatically ontology learning from Web pages and considered some key problems about extracting concepts and interrelationships in ontology learning.