Rethinking Chinese Word Segmentation: Tokenization, Character Classification, or Wordbreak Identification

Chu-Ren Huang, Petr Simon, Shu-Kai Hsieh, Laurent Prévot. Rethinking Chinese Word Segmentation: Tokenization, Character Classification, or Wordbreak Identification. In ACL 2007, Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, June 23-30, 2007, Prague, Czech Republic. The Association for Computer Linguistics, 2007. [doi]

Abstract

Abstract is missing.