Rules-based Chinese Word Segmentation on MicroBlog for CIPS-SIGHAN on CLP2012
Jing Zhang, Degen Huang, Han Xia, Wei Wang · 2012
In this evaluation, we have taken part in the task of the Word Segmentation on Chinese MicroBlog. In this task, after analysing the feature of the MicroBlog and the result of our original Chinese word segmentation system, four Optimization Rules are proposed to opti-mize the segmentation algorithm for Chinese word segmentation on MicroBlog corpora. The optimized segmentation system is based on character-based and word-based Condi-tional Random Fields (CRFs). Experiments show that the optimized segmentation system can obviously improve the performance of CWS on MicroBlog corpora. 1