Based On Ontology Information Extraction System

information source. As it's hard for user to find the needed information by traditional search engineering, the accuracy of search engineering is emphasized. Of all the ways to raise the accuracy, to make the engineering understanding the content of the information sources is one of them, which is the diretion of the development of senmatic WEB raising in the area of INTERNET researching at present. Based on the technology of marking the XML information constructure, the technology of senmatic WEB marks the content of information, and as a result, the search based on content is accomplished. As a boring work, manual marking waste much time, so it is necessary for us to adopt the technology of Information Extraction to extract the senmatic information automatically.In this paper, based on the introduction of the system architecture and the basic knowledge of ontology, a new approach to extracting information from normal document based on an application ontology that describes a domain of interest is discussed. In this approach, combined the Information Extraction with ontology, the method of using the concepts, relations and keywords of domain ontology to generate Information Extraction rule automatically and then do grammar parsing on the document is adopted, and in the end the results of extracting and the analysis of it are displayed.