Auto-maintained document classification
作者： Yigal S. Dayan , Josemina M. Magdalen , Gil Fuchs , Irit Maharian , Yariv Tzaban
DOI:
关键词:
摘要: Machines, systems and methods for maintaining a representative data set in document classification system, the method comprising: including an initial of seed (RDS) implemented knowledge base (KB), wherein KB is trained to classify documents provided system based on analysis included RDS rules, includes balanced number across plurality classes; updating by adding or removing from feedback received about accuracy one more system; retraining KB, performed occurrence events.
lens.org 参考文章(5)
Cyril Goutte, Eric Gaussier, Incremental training for probabilistic categorizer ,(2005)
Philip Shi-lung Yu, Haixun Wang, Jian Yin, System and method for learning models from scarce and skewed training data ,(2006)
Josemina Magdalen, Ronen Hod, Yoram Nelken, Dani Cohen, Amir Navot, Sam Michelson, Nissan Hajaj, Avi Margalit, Tsachy Shacham, Beth Lanin, Randy Jessee, Software tool for training and testing a knowledge base ,(2004)
Josemina Magdalen, Yoram Nelken, Dani Cohen, Nissan Hajaj, System and method for electronic communication management ,(2004)
Alex Dowgailenko, Steve Pettigrew, Isabelle Giguère, Stephen Ludlow, Agostino Deligia, Reconfigurable Model for Auto-Classification System and Method ,(2012)