A study of information extraction from free text based on chinese framenet tagging

Information extraction (IE) is a main approach for constructing database from free text corpus and for automatic collecting information. Frame semantic tagging is suggested to be the base for rule-building in IE. IE based on frame semantic tagging uses a uniform approach to guide the process of IE. Processing at a finer granularity level, the approach has a universal appeal for IE in domains showing strong semantic rules. A system called BA IE (book abstract information extract ion system), which is based on frame semantic, is designed and used to extract information from book abstract. The result shows that the approach is feasible and has practical promise.