Typographical and Orthographical Spelling Error Correction

Abstract

This paper focuses on selection techniques for best correction of misspelt words at the lexical level. Spelling errors are introduced by either cognitive or typographical mistakes. A robust spelling correction algorithm is needed to cover both cognitive and typographical errors. For the most effective spelling correction system, various strategies are considered in this paper: ranking heuristics, correction algorithms, and correction priority strategies for the best selection. The strategies also take account of error types, syntactic information, word frequency statistics, and character distance. The findings show that it is very hard to generalise the spelling correction strategy for various types of data sets such as typographical, orthographical, and scanning errors.

Resources

Details