Soochow University Word Segmenter for SIGHAN 2012 Bakeoff
Fang Yan, Zhongqing Wang, Shoushan Li, LI Zhong-guo, Richen Xu, Leixin Cai · 2012
This paper presents a Chinese Word Segmentation system on MicroBlog corpora for the CIPS-SIGHAN Word Segmentation Bakeoff 2012. Our system employs Conditional Random Fields (CRF) as the segmentation model. To make our model more adaptive to MicroBlog, we manually analyze and annotate many MicroBlog messages. After manually checking and analyzing the MicroBlog text, we propose several pre-processing and post-processing rules to improve the performance. As a result, our system obtains a competitive F-score in comparison with other participating systems.