System and method for retrieving documents or sub-documents based on examples
作者： Huaiyu Zhu , Christopher Campbell , Tomas Costello , Shivakumar Vaithyanathan , Mahesh Joshi
DOI:
关键词: Feature vector 、 Data mining 、 Cascade 、 Training set 、 Classifier (UML) 、 Computer science 、 Information retrieval
摘要: Disclosed are a system, method, and program storage device implementing the method of extracting information, wherein comprises inputting query; searching database documents based on retrieving from matching query using plurality classifiers arranged in hierarchical cascade classifier layers, each set weighted training data points comprising feature vectors representing any portion document; weighing an output according to rate success terms being matched by layer cascade, is performed terminal classifier.
google.ca 参考文章(7)
Thomas Y. Woo, Modular packet classification ,(2001)
Byron Edward Dom, Soumen Chakrabarti, Prabhakar Raghavan, Rakesh Agrawal, Multilevel taxonomy based on features derived from training documents classification using fisher values as discrimination values ,(1998)
Long Zhu, ZhenQiu Zhang, ZiQing Li, Method for boosting the performance of machine-learning classifiers ,(2005)
Yaron Galai, Oded Itzhak, Ilan Itzhak, System and method for automated mapping of keywords and key phrases to documents ,(2003)
Gordon G. Sun, Michael E. Palmer, Hongyuan Zha, Method and apparatus for measuring similarity among electronic documents ,(1999)
Gopalan Ravichandran, William Mabry Tyson, Mark Edward Stickel, Karen Louise Myers, James Frederick Arnold, David L Martin, Jerry Robert Hobbs, Douglas E Appelt, Megumi Di Kameyama, John S Bear, David J Israel, Information retrieval by natural language querying ,(2000)
Edy S. Liongosari, Kelly L. Dempski, Scott Kurth, Kishore Swaminathan, Knowledge management tool ,(2007)