Copyright Tong Zhang
This page contains some code that either my coauthors or I wrote.
This is an unsupervised pretraining method for Chinese that can take advantage of n-gram (multi-character) information, achieving better results than BERT.
implementaiton of various text catgorization methods using neural networks
CNN (NAACL 15)
Semisupervised Learning (NIPS 15)
LSTM (ICML 16)
DPCNN (ACL 17)
for nonlinear prediction using the
This is a regularized version of boosted decision trees (forest) with improved performance.