基于英、维匹配技术的跨语言领域本体构建方法研究  

RESEARCH ON CROSS-LANGUAGE DOMAIN ONTOLOGY CONSTRUCTION METHOD BASED ON ENGLISH AND UYGHUR LANGUAGE MATCHING TECHNOLOGY

作　　者：库都来提.阿布都热合曼 哈妮克孜.伊拉洪 艾斯卡尔.艾木都拉 Kudrat Abdurahman;Hankiz Yilahun;Askar Hamdulla(Xinjiang University, Ukumqi 830046, Xinjiang, China)

机构地区：[1]新疆大学,新疆乌鲁木齐830046

出　　处：《计算机应用与软件》2018年第6期18-22,共5页Computer Applications and Software

基　　金：国家社科基金项目(13BYY062)

摘　　要：对其他研究或应用中的英语领域本体进行重用,为构建维吾尔语领域本体提供了极大的便利。提出一种基于英语、维吾尔语匹配技术的跨语言领域本体构建方法,对收集的领域本体集合进行三元组自动抽取。使用跨语言技术进行英语、维吾尔语匹配,通过Apache Jena工具构建维吾尔语领域本体。使用Protégé5.0工具对构建的本体进行语法验证。该方法弥补了维吾尔语中使用跨语言技术来构建领域本体的研究空缺。实验结果表明该算法在领域本体构建中具有可行性和有效性。Reuse of English domain ontology in other research or application provides great convenience for constructing Uyghur domain ontology. This paper proposed a cross-linguistic domain ontology construction method based on English and Uyghur language matching technology. The collection of domain ontology sets was automatically extracted by triples,and cross-language techniques were used for English and Uighur matching. The Uyghur domain ontology was constructed through Apache Jena tool. Finally,we used the Protégé tool to perform syntax validation on the constructed ontology. This method made up for the gap in Uighur＇s use of cross-language technology to construct domain ontology.At the same time,this method was verified by experiments. Experimental results show that the algorithm is feasible and effective in domain ontology construction.

关 键 词：领域本体 本体重用 三元组 跨语言 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]