The CIPS-SIGHAN CLP 2012 Chinese Word Segmentation on MicroBIog Corpora Bakeoff

摘要

The CIPS-SIGHAN CLP 2012 Chinese Word Segmentation on MicroBIog Corpora Bakeoff was held in the autumn of 2012. This bake-off task of Chinese word segmentation is focused on the performance of Chinese word segmentation algorithms on MicroBIog corpora. 17 groups submitted 20 results, among which the best system has all the P, R and F values near 95%, and the average values of the 17 systems are 0.8931, 0.8981 and 0.8953, respectively.