An approach to improving the quality of part-of-speech tagging of Chinese text

The disambiguation of multicategory words is one of the difficulties in part-of-speech tagging, which greatly affects the processing quality of corpora. Aiming at this question, we describe an approach to correcting the part-of-speech tagging of multicategory words automatically. It acquires correction rules for the part-of-speech tagging of multicategory words from right-tagged corpora based on the theory of rough sets and data mining, and then automatically corrects the corpora´s part-of-speech tagging of multicategory words based on these rules. According to the results of close-test and open-test on the corpus of 500,000 Chinese characters, the accuracy of corpora can be increased by 11.32% and 5.97% respectively.