On Trajectory Augmentations for Off-Policy Evaluation
Ge Gao, Qitong Gao, et al.
ICLR 2024
This paper describes an application of the Minimum Classification Error (MCE) criterion to the problem of recognizing online unconstrained-style characters and words. We describe an HMM-based, character and word-level MCE training aimed at minimizing the character or word error rate while enabling flexibility in writing style through the use of multiple allographs per character. Experiments on a writer-independent character recognition task covering alpha-numerical characters and keyboard symbols show that the MCE criterion achieves more than 30 percent character error rate reduction compared to the baseline Maximum Likelihood-based system. Word recognition results, on vocabularies of 5k to 10k, show that MCE training achieves around 17 percent word error rate reduction when compared to the baseline Maximum Likelihood system. © 2006, IEEE. All rights reserved.
Ge Gao, Qitong Gao, et al.
ICLR 2024
Shuang Chen, Herbert Freeman
International Journal of Pattern Recognition and Artificial Intelligence
John R. Kender, Rick Kjeldsen
IEEE Transactions on Pattern Analysis and Machine Intelligence
Kaiyuan Zhang, Guanhong Tao, et al.
ICLR 2023