Correcting Real-Word Spelling Errors: A New Hybrid Approach
This work addresses a specific challenge in natural language processing for text processing applications, but it appears incremental as it builds on prior trigram and constraint grammar techniques.
The paper tackles the problem of correcting real-word spelling errors, which conventional methods cannot detect, by proposing a new hybrid approach that combines statistical and syntactic knowledge, achieving practical improvements over existing models like WordNet-based and fixed window size methods.
Spelling correction is one of the main tasks in the field of Natural Language Processing. Contrary to common spelling errors, real-word errors cannot be detected by conventional spelling correction methods. The real-word correction model proposed by Mays, Damerau and Mercer showed a great performance in different evaluations. In this research, however, a new hybrid approach is proposed which relies on statistical and syntactic knowledge to detect and correct real-word errors. In this model, Constraint Grammar (CG) is used to discriminate among sets of correction candidates in the search space. Mays, Damerau and Mercer's trigram approach is manipulated to estimate the probability of syntactically well-formed correction candidates. The approach proposed here is tested on the Wall Street Journal corpus. The model can prove to be more practical than some other models, such as WordNet-based method of Hirst and Budanitsky and fixed windows size method of Wilcox-O'Hearn and Hirst.