Previous: Ontology-based text categorization
Up: IICA: An Ontology-based Internet Navigation System
Next: Evaluation
Previous Page: Ontology-based text categorization
Next Page: State Diagram Method

Information Extracting and Reorganization

This section describes information extracting and reorganization using heuristics. We collected and analyzed the sightseeing pages in Japanese. As the result, it was found that it is possible to extract and reorganize specific information form pages using heuristics based on expression patterns and phrases.

1. State Diagram Method It is the method to analyze and extract specific items according to a state diagram. For example, in case of extracting information about transport facilities, IICA analyzes in such sequence as,

bus stop(point) ¢ª bus ¢ª bus stop(point) ¢ª walk ¢ª ¡Ä.

2. Rule-base method It is the method to extract specific items according to attributes and rules defined in ontologies. This method can be widely applied to various information on the WWW.

• State Diagram Method
• Rule-based method