Invention Application
- Patent Title: AUTOMATIC DATA CLEANING FOR MACHINE LEARNING CLASSIFIERS
- Patent Title (中): 机器学习分类器的自动数据清理
-
Application No.: PCT/US2012/025930Application Date: 2012-02-21
-
Publication No.: WO2012115958A2Publication Date: 2012-08-30
- Inventor: MALIK, Hassan, H. , OLOF-ORS, Mans
- Applicant: THOMSON REUTERS GLOBAL RESOURCES , MALIK, Hassan, H. , OLOF-ORS, Mans
- Applicant Address: Neuhofstrasse 1 CH-6304 Baar CH
- Assignee: THOMSON REUTERS GLOBAL RESOURCES,MALIK, Hassan, H.,OLOF-ORS, Mans
- Current Assignee: THOMSON REUTERS GLOBAL RESOURCES,MALIK, Hassan, H.,OLOF-ORS, Mans
- Current Assignee Address: Neuhofstrasse 1 CH-6304 Baar CH
- Agency: DIVITA, Bartholomew J. et al.
- Priority: US13/046,266 20110311; US61/445,236 20110222
- Main IPC: G06K9/62
- IPC: G06K9/62
Abstract:
Systems and techniques for improving the training of machine learning classifiers are disclosed. A classifier is trained using a set of validated documents that are accurately associated with a set of class labels. A subset of non-validated documents is also identified and is used to further train and improve accuracy of the classifier.
Information query
