基于两层向量空间模型和模糊FCA本体学习方法

An Ontology Learning Method Based on Double VSM and Fuzzy FCA

本体是WWW进化为语义Web版本的瓶颈,手工构造本体费时费力,本体学习技术使得在文本中自动构造本体成为可能,但存在通用性差和准确性低等问题.提出以面向对象思想的分析方法为基础,把传统的单层文本向量空间模型(VSM)改进为2层向量空间模型(double vector space model,D-VSM),该模型不仅具有属性特性,而且还具有很强的关系特性.在此模型的基础上,引入模糊形式概念分析(fuzzy formal concept analysis,FFCA)本体学习技术.该技术充分考虑D-VSM模型中的数据分布特点,较好地解决本体学习通用性、本体关系获取等问题.基于上述方法实现一个本体学习工具,为本体的(半)自动构造提供有力的支持.

Ontology realization poses as the maior hindrance to the evolution of World Wide Web into semantic Web. The manual construction of ontology demands large amount of labor as well as lasts for long durations. Ontology learning technology makes it possible for the automatic building of ontology in texts and greatly accelerates the speed of construction; yet, the technology is constrained by its lack of generality and accuracy. Based on the object-oriented analytical methods, a formal spatial description on ontology learning data source is performed. The authors revise the classical descriptive method for texts, that is, the object-oriented single vector space model （VSM） and propose a double vector space model （D-VSM）, specifically, verbal layer and noun layer. This model is characterized by the inclusion of diverse attributes and solid relations. To further cope with information redundancy associated with FCA method and to improve the accuracy of concept abstraction, the fuzzy formal concept analysis （FFCA） ontology learning technology is introduced, which can fully explore the distributed property of data in DVSM and specialize in solving issues like ontology continuity, ontology relations obtainment, etc. An ontology learning tool is created based on DV-FFCA methodology, which provides powerful support for automatic （ semi-automatic ） ontology construction.