Turkish spelling error detection and correction by using word n-grams

Author

Dalkiliç, Gökhan ; Çebi, Yalçin

Author_Institution

Comput. Eng. Dept., Dokuz Eylul Univ., Izmir, Turkey

fYear

2009

fDate

2-4 Sept. 2009

Firstpage

1

Lastpage

4

Abstract

N-grams can be used for spelling check and correction processes. The first step to use n-grams is to find the language specific n-grams by using a corpus. But a corpus cannot be big enough to contain all the possible word n-grams. Back-off smoothing technique is one of the techniques to estimate the frequency of the unknown n-grams in a corpus. By using Back-off technique and the Minimum Edit Distance (MED) algorithm, a program was developed to check spelling errors and suggest corrections in a sentence typed in Turkish. The results were compared with the results of Microsoft Word 2003 proofing tools, and found to be much better.

Keywords

C language; probability; text analysis; Turkish language; back-off smoothing technique; minimum edit distance algorithm; spelling error correction; spelling error detection; word n-grams; Bayesian methods; Computer errors; Computer languages; Error correction; Frequency estimation; Maximum likelihood estimation; Probability; Smoothing methods; Sparse matrices;

fLanguage

English

Publisher

ieee

Conference_Titel

Soft Computing, Computing with Words and Perceptions in System Analysis, Decision and Control, 2009. ICSCCW 2009. Fifth International Conference on

Conference_Location

Famagusta

Print_ISBN

978-1-4244-3429-9

Electronic_ISBN

978-1-4244-3428-2

Type

conf

DOI

10.1109/ICSCCW.2009.5379481

Filename

5379481