Active Learning with Confidence

Active learning is a machine learning approach to achieving high-accuracy with a small amount of labels by letting the learning algorithm choose instances to be labeled. Most of previous approaches based on discriminative learning use the margin for choosing instances. We present a method for incorporating confidence into the margin by using a newly introduced online learning algorithm and show empirically that confidence improves active learning.

• Type: Conference
• Year: 2008
• Where: ACL
• Authors: Mark Dredze, Koby Crammer
• Keywords: ACL 2008, Active Learning, Algorithm Choose Instances, Computational Linguistics, Machine Learning Approach