Word Segmentation on Chinese Mirco-Blog Data with a Linear-Time Incremental Model
Kaixu Zhang, Maosong Sun, Changle Zhou · 2012
This paper describes the model we designed for the word segmentation bakeoff on Chinese micro-blog data in the 2nd CIPS-SIGHAN joint conference on Chinese language processing. We presented a linear-time incremental model for word segmentation where rich features including character-based features, word-based features as well as other possible features can be easily employed. We report the performances of our model on four datasets in the SIGHAN bake-off 2005. After adding more features designed for the micro-blog data, the performance of our model is further improved. The F-score of our model for this bake-off is 0.9478 and 44.88 % of the sentences are segmented correctly.