Chinese Ontology Learning Technology Based On Text2Onto

With the research on the Semantic Web, the next generation of internet, ontology is becoming an important tool in the artificial intelligence and knowledge engineering. It is of great significance to the acquisition, representation, analysis and application of knowledge areas. Construct ontology by handwork is a fussy and a troubling task, and an issue named"ontology bottleneck", the lack of efficient ways to build ontologies, has been coming up to generate ontologies. Therefore, accessibility of ontology has been recognized by the academic community as one of the great challenges which are constraining the success of the Semantic Web. Constructing ontology in semiautomatic or automatic way at low cost is a key problem of ontology research. Capturing domain knowledge from existed information (such as texts, dictionaries, remnant Knowledge, WWW documents, etc) to build or expand ontology automatically, which is called Ontology Learning, is an effective way of ontology development.Correspondingly, it is critical for us to acquire Chinese ontology in order to extend and implement Semantic Web in China. It has become an important subject in the Chinese Semantic Web to acquire ontology from corpus of different fields, and to enhance the quality of the results for effective application.In this paper, It extends discussion and research around the access technology of Chinese ontology based on the framework of Text2Onto aiming at characteristics of Chinese and differences between Chinese and English, and the ICTCLAS have been used.Firstly, the paper introduces the advantages, system architecture, working principle and key algorithms of Text2Onto.Then it puts forward to Chinese ontology study technology framework based on Text2Onto aiming at the problem existed in area of Chinese ontology study. It also makes more detailed introduction to some key technical issues under this framework respectively, including the Chinese corpus preprocessing, concepts extraction and semantic relation extraction; given the specific algorithm of the extraction and filtering of Chinese concepts.Finally, it analyzes the existing ontology learning system architecture, integrates Chinese word segmentation at the basis of Text2Onto, adds the algorithms of extraction and filtering of Chinese concepts, and achieves the Chinese ontology learning system framework.Through experiments, it shows that the Chinese ontology study technology research based on Text2Onto is a very meaningful attempt for technology of Chinese ontology accessing, it offers a initial solution of the Chinese concepts extraction and filtration problem, and it has laid a good foundation for the follow-up study of Chinese ontology study technology research.