-oriented Information Extraction Of Ontology Design And Realization

Nowadays, Web becomes the main information resource. However it is not easyfor people to get the information they really interested in on the Web, since Web pagesare semi-structure or non-structure, the hyperlinks are disordered and the data aremassive and dynamic.In the long term, the essential method to solve the above contradiction is tochange disorderly data into orderly knowledge, to make computers understand theWeb information and the need of people. Tim Berners-Lee proposed the concept ofSemantic Web in 1998. It is an extension of the current Web in which information isgiven well-defined meaning, better enabling computers and people to work incooperation.The Semantic Web uses a multi-level framework to achieve its goal. Ontologylocates in the level from textual description to knowledge-based reasoning. So it isimportant to develop ontology for the Semantic Web.Ontology is an explicit specification of a conceptualization. It defines the basicconcepts and relations comprising the vocabulary of a topic area. This makes theseconcepts and relations have explicit and exclusive definitions in certain scope. Thenpeople can communicate with machines freely.Ontology combined with information extracting technology, it is called theontology-based information extracting system. The advantage of this informationextracting method is it does not depend on the structure of Web pages. We useontology to describe and present the knowledge database of information extractingsystem, it better the semantic expressing ability of extracting template. We can makethe extracting result more veracious by emphasize on one special scope. Theinformation extracting method based on ontology can map word to concept and entity,incarnate the true meaning of the words well, moreover it can embody the relationbetween the words by class succeed relation of ontology, all this make the informationextracting system more powerful.In this paper, we applied the ontology-based information extracting method onstock information extracting. We built up stock ontology, use its concepts,relationsand key words to create extracting rules automatically. After the pretreatment to thearticles, we use those rules to do information extraction, and save the results in...