... compared the perfor-mance of the models, including SVMs, CRFs,MBL, and TBL, in Chinese chunking. In the ex-periments, we used the feature WORD+POS andset the window size as 2 for the first ... different sizes of training sets, including 1%, 2%, 5%, 10%, 20%,50%, and 100% of the total training data. In our experiments, we used all the default pa-rameter settings of the packages. Our ... voting methodsaccording to the characteristics of the chunkingtask. We proposed the Tag-Extension approach toresolve the special problems of Chinese chunkingby extending the chunk tags.The...