Abstract—Spell checking and error correcting applications for agglutinative languages is quite different from other languages, such as English. Thus, to develop spell checking and error correcting software, morphological analysis and mathematical preliminaries are required in agglutinative languages as Turkish. In this study, an application is developed for spell checking and error correcting for Turkish. The application uses Turkish corpus and morphological structure. nZemberek is used for Turkish dictionary suitability of the roots of words and compliance of suffixes to Turkish rules were determined using. The application utilizes n-gram depending on word length and the edit distance method for the correction of words. The application completes the spell check with a 95% success rate and suggests the correct options for spelling errors with an 86% success rate.
Index Terms—Agglutinative languages, edit distance, n-gram, spell checking, spell error correcting.
E. Yılmaz İnce is with the Computer Technologies Department, University of Suleyman Demirel, Isparta, 32200 TURKEY (e-mail: ebruince@sdu.edu.tr).
[PDF]
Cite:E. Yılmaz İnce, "Spell Checking and Error Correcting Application for Turkish," International Journal of Information and Electronics Engineering vol. 7, no. 2, pp. 68-71, 2017.