一种基于同义词词林的中文大规模本体映射方案

Tongyici Cilin-based Mapping Approach for Large-scale Chinese Ontology

本体映射是解决本体异构问题的重要途径和手段,中文知识是网络开放知识库的重要组成部分,但现有的中文本体映射系统在面对大规模本体映射任务时,显得效率较低且可用性不高,目前仍缺乏针对中文大规模本体映射的相关系统。为了解决中文大规模本体的映射问题,设计并实现了一个面向中文的大规模本体映射系统。首先,提出了一种基于拟核力场势函数的大规模本体压缩方法;其次,提出了一种基于同义词词林的中文概念等价关系确定算法;再次,实现了大规模中文本体映射的原型系统;最后,将本系统与相似度计算相关典型算法进行比较,证明其具备一定的可用性和较高的总体性能。

Ontology mapping is an important way to solve the problem of the ontology heterogeneous.The Chinese knowledge is an important part of the online knowledge base,but there is still lack of relevant system for Chinese large scale ontology mapping.While facing the large-scale ontology mapping task,current Chinese ontology mapping system has low efficiency and its availability is not high.In order to solve the Chinese ontology mapping problem,this paper put forward a kind of Tongyici Cilin-based ontology mapping architecture,firstly presented a data field-based method to compress the Chinese large-scale ontology,secondly purposed a Tongyici Cilin-based algorithm for the Chinese equivalent-class discovery,thirdly implemented a prototype system for Chinese large-scale ontology mapping,finally compared the system with the other typical similarity computing algorithm.The result proves that it has higher overall performance and usability.