一种领域概念非分类关系的获取方法  

Method for non-taxonomical relations from domain concepts

作　　者：董丽丽[1] 胡云飞[1] 张翔[1] 

机构地区：[1]西安建筑科技大学信息与控制工程学院,西安710055

出　　处：《计算机工程与应用》2013年第4期157-161,共5页Computer Engineering and Applications

基　　金：陕西省自然科学基金(No.2009JM8006);陕西省教育厅专项科研项目(No.2010JK620)

摘　　要：领域概念非分类关系的获取是本体学习的一项重要任务,提出了一种基于非监督学习的非分类关系自动获取方法。该方法首先通过关联规则获取特定领域概念对,然后将概念对之间的高频动词作为候选的非分类关系标签,接着利用VF*ICF度量法来确定非分类关系标签,最后通过对数似然比评估方法将得到的非分类关系标签分配给对应的领域概念对。实验结果表明该方法可以有效提高非分类关系抽取的准确率和召回率。Research on non-taxonomical relations from domain concepts is an important task in ontology learning. This paper presents an acquiring method for non-taxonomical relations of special domain based on unsupervised learning. This method em- ploys association rules to get the concept pairs of special domain, regards the high frequency verbs of the concept pairs as the candidate non-taxonomical relations labels, non-taxonomical relations labels is determined by VF＊ICF metrics, use log likeli- hood ratio to assign the non-taxonomical relations labels to corresponding domain concepts pairs. Experimental results demon- strate the increment of the accuracy and comoleteness of the non-taxonomical relations extraction.

关 键 词：本体学习 非监督学习 关联规则 非分类关系 VF＊ICF度量法 对数似然比 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]