Combining Trigram and Automatic Weight Distribution in Chinese Spelling Error Correction
-
Abstract
The researches on spelling correction aiming at detecting errors intexts tend to focus on context-sensitive spelling error correction,which is more difficult than traditional isolated-worderror correction. A novel and efficient algorithm for the system ofChinese spelling error correction, CInsunSpell, is presented. Inthis system, the work of correction includes two parts: checking phaseand correcting phase. At the first phase, a Trigram algorithm within onefixed-size window is designed to locate potential errors in localarea. The second phase employs a new method of automatically anddynamically distributing weights among the characters in the confusion setas well as in the Bayesian language model. The tactics used aboveexhibits good performances.
-
-