Paper: Reducing the False Alarm Rate of Chinese Character Error Detection and Correction

ACL ID W10-4107
Title Reducing the False Alarm Rate of Chinese Character Error Detection and Correction
Venue Joint Conference on Chinese Language Processing
Session Main Conference
Year 2010
Authors

The main drawback of previous Chinese cha- racter error detection systems is the high false alarm rate. To solve this problem, we propose a system that combines a statistic method and template matching to detect Chinese character errors. Error types include pronunciation- related errors and form-related errors. Possible errors of a character can be collected to form a confusion set. Our system automatically gene- rates templates with the help of a dictionary and confusion sets. The templates can be used to detect and correct errors in essays. In this paper, we compare three methods proposed in previous works. The experiment results show that our system can reduce the false alarm sig- nificantly and give the best performance on f- score.