Bootstrapping-based Automatic Acquisition of Domain Concepts for Ontology Construction  

作　　者：YANG Yuehua DU Junping ZI Lingling 

机构地区：[1]Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China [2]School of Electronic and Information Engineering, L iaoning Technical University, Huludao 125105, China

出　　处：《Chinese Journal of Electronics》2013年第2期313-318,共6页电子学报（英文版）

基　　金：This work is supported by the National Basic Research Program of China （973 Program） （No.2012CB821200 No.2012CB821206）, the National Natural Science Foundation of China （No.91024001, No.61070142）, and Beijing Natural Science Foundation （No.4111002）.

摘　　要：The domain concept is one of the key el- ements of ontology. In order to automatically acquire the domain concepts during the domain ontology construction, we proposed a novel Bootstrapping-based automatic acqui- sition algorithm of domain concepts. In our work, the com- pound words are extracted according to the combination conditions of the mutual information and the information entropy. The candidate domain concepts determinant con- ditions based on the co-occurrence sentences frequency are presented. Besides, to avoid omitting the domain concepts with the lower frequency or semantically similar to other domain concepts, the semantic factor is introduced. The experiments results have demonstrated that the compound domain concepts and the semantically similar domain con- cepts with the lower sentences frequency can also be ex- tracted by using the proposed algorithm. And the pro- posed algorithm has obtained higher precision and recall, so it is effective and feasible.

关 键 词：BOOTSTRAPPING Automatic acquisition of concepts Compound words extraction~ Semantic factor. 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TH122[自动化与计算机技术—控制科学与工程]