... UPENN Chinese Treebank-4(CTB4). Wepresented an empirical study of Chinese chunk-ing on this corpus. First, we made an evaluation on the corpus to clarify the performance of state- of- the-art models ... in this study.Training TestNum of Files 728 110Num of Sentences 9,878 5,290Num of Words 238,906 165,862Num of Phrases 141,426 101,449Table 2: Information of the CTB4 Corpus3 Chinese Chunking3.1 ... conducted an empirical study of Chinese chunking. We compared the performance of four models, SVMs, CRFs, MBL, and TBL.We also investigated the effects of using differentsizes of training data....