Chu-Ren Huang Petr Simon Shu-Kai Hsieh Laurent Prévot Rethinking Chinese Word Segmentation: Tokenization, Character Classification, or Wordbreak Identification. 2007 ACL http://aclweb.org/anthology-new/P/P07/P07-2018.pdf conf/acl/2007 db/conf/acl/acl2007.html#HuangSHP07