Chinese Word Spelling Correction Based on N-gram Ranked Inverted Index List

Spelling correction can assist individuals to input text data with machine using written language to obtain relevant information efficiently and effectively in. By referring to relevant applications such as web search, writing systems, recommend systems, document mining, typos checking before printing is very close to spelling correction. Individuals can input text, keyword, sentence how to interact with an intelligent system according to recommendations of spelling correction. This work presents a novel spelling error detection and correction method based on N-gram ranked inverted index is proposed to achieve this aim, spelling correction. According to the pronunciation and the shape similarity pattern, a dictionary is developed to help detect the possible spelling error detection. The inverted index is used to map the potential spelling error character to the possible corresponding characters either in character or word level. According to the N-gram score, the ranking in the list corresponding to possible character is illustrated. Herein, E-How net is used to be the knowledge representation of tradition Chinese words. The data sets provided by SigHan 7 bakeoff are used to evaluate the proposed method. Experimental results show the proposed methods can achieve accepted performance in subtask one, and outperform other approaches in subtask two.