@article{LI2009, 
author = {Jingyang LI and Maosong SUN},
title = {Non-Independent Term Selection for Chinese Text Categorization},
year = {2009},
journal = {Tsinghua Science and Technology},
volume = {14},
number = {1},
pages = {113-120},
keywords = {Chinese text categorization, term selection, dimentionality},
url = {https://www.sciopen.com/article/10.1016/S1007-0214(09)70016-1},
doi = {10.1016/S1007-0214(09)70016-1},
abstract = {Chinese text categorization differs from English text categorization due to its much larger term set (of words or character n-grams), which results in very slow training and working of modern high-performance classifiers. This study assumes that this high-dimensionality problem is related to the redundancy in the term set, which cannot be solved by traditional term selection methods. A greedy algorithm framework named "non-independent term selection" is presented, which reduces the redundancy according to string-level correlations. Several preliminary implementations of this idea are demonstrated. Experiment results show that a good tradeoff can be reached between the performance and the size of the term set.}
}