文章基本信息

标题：AUTOMATIC ARABIC ONTOLOGY GENERATION FOR THE ANIMAL KINGDOM (NAAO)
本地全文：下载
作者：DALIA FADL ; SAFIA ABBAS ; MOSTAFA AREF 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：1
页码：227
出版社：Journal of Theoretical and Applied
摘要：Ontology is the gateway for the interaction between human and the machines because it facilitates the gaining of the information for the end users. The semantic web terms and vocabulary are considered as form of ontology. So the improvement of the ontology helps in the semantic web progration. Arabic ontology is a critical natural language processing field; it helps to enrich the Arabic language resources. Although, the searchers started to focus their efforts creating ontologies in Arabic language, the Arabic terms and fields have not yet been covered. This paper introduces an innovative framework, annotated as NAAO (Novel Automatic Arabic Ontology), which automates the ontology generation process from XML documents. The novelty of NAAO resides in generating the Arabic ontology, in the form of XML graph schema (XSG), from semi-structured data (XML documents associated with graph schema). The automation process entails four main phases (extrication, XML schema parsing, ontology generation and refinement and evaluation). Extrication phase, where all the data required for the ontology generation is extricated from the information source. XML schema parsing phase, where the extracted data is going to be investigated and the hierarchical analysis to identify all the parts of the ontology is going to be created. Ontology generation phase deal with the production of the Arabic ontology (classes, elements, and relations). Finally, refinement and evaluation phase that deals with improvements of the Arabic ontology. Moreover, the paper comprises versatile examples for an automatic generation to Arabic ontologies regarding the animal kingdom. Such as the invertebrate's ontology, in which the XSG is automatically extracted using 103 XML documents, 320 concepts (classes), 603 elements and 783 relations. Finally, NAAO enjoys certain advantages than others since it shows an automatically generate Arabic ontology from semi-structured data (XML file). It provides mapping connections to ensure the right relationships with the classes and the elements to its corresponding nodes in the XML documents and supplies huge ontology contents (concepts elements and relations). Moreover, NAAO offers an automatic evaluation of the generated Arabic ontology using cosine similarity measurements.
关键词：Arabic Ontology; Ontology Learning; Ontology Generation; XML Schema; Evaluation