面向知识网格的本体学习研究

A Study on Ontology Learning for the Knowledge Grid

网格计算正在从单纯的面向大型计算的分布式资源共享发展为一种面向服务的架构,以实现透明而可靠的分布式系统集成。网格智能是指如何获取、预处理、表示和集成不同层次的网格服务(如HTML/XML/RDF/OWL文档、服务响应时间和服务质量等)的数据和信息,并最终转换为有用的智能(知识)。因为高层知识将在未来的网格应用起到越来越重要的作用,本体是知识网格实现的关键。文章提出了一种实现从Web文档中本体(半)自动构建的本体学习框架WebOntLearn,并讨论了本体学习中领域概念的抽取、概念之间关系的抽取和分类体系的自动构建等关键技术。

Grid Computing is evolving from the merely sharing of distributed resources for large computational tasks to the developing of Grid as a service-oriented architecture for transparent and reliable distributed system integration.The paradigm of Grid computing complements the current approach of Semantic Web and Web Services by providing an infrastructure to handle large-scale distributed enterprise information systems.Grid intelligence refers to an emerging research field that addresses on how the data and information available at different levels of Grid services(e.g.,HTML/XML/RDF/OWL etc)can be effectively acquired,preprocessed,represented,interchanged,integrated and eventually converted into useful intelligences(knowledge).As higher-level knowledge is going to play a more important role in the future Grid applications,ontology is the key of the Knowledge Grid.This paper first proposes a framework of ontology learning from web pages.Then key technologies of ontology learning such as domain concepts extraction and semantic relationships between concepts and taxonomy automatic construction are discussed.