A Chinese Part of Speech Tagging Method Based on Maximum Entropy Principle
Lin Hong, Yuan Chun-fa, Guo Shujun · Jisuanji gongcheng · 2004
A lot of researches have been made on the application of the maximum entropy modeling in the natural language processing during recent years. This paper presents a new Chinese part of speech tagging method based on maximum entropy principle because Chinese is quite different from many other languages. The feature selection is the key point in this system which is distinct from the one used in English. Experiment results have shown that the part of speech tagging accuracy ratio of this system is up to 97.34%.