Real-word spelling correction using Google Web 1T n-gram with backoff

Author

Islam, Amunul ; Inkpen, Diana

Author_Institution

Dept. of Comput. Sci., Univ. of Ottawa, Ottawa, ON, Canada

fYear

2009

fDate

24-27 Sept. 2009

Firstpage

1

Lastpage

8

Abstract

We present a method for correcting real-word spelling errors using the Google Web 1T n-gram data set and a normalized and modified version of the longest common subsequence (LCS) string matching algorithm. Our method is focused mainly on how to improve the correction recall (the fraction of errors corrected) while keeping the correction precision (the fraction of suggestions that are correct) as high as possible. Evaluation results on a standard data set show that our method performs very well.

Keywords

Internet; search engines; spelling aids; string matching; text analysis; Google Web 1T n-gram data set; LCS; correction precision; correction recall; longest common subsequence string matching algorithm; real-word spelling error correction; text analysis; Computer errors; Computer science; Dictionaries; Error correction; Humans; Learning systems; Machine learning; Machine learning algorithms; Performance evaluation; Voting; Google web 1T; Real-word; n-gram; spelling correction;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Language Processing and Knowledge Engineering, 2009. NLP-KE 2009. International Conference on

Conference_Location

Dalian

Print_ISBN

978-1-4244-4538-7

Electronic_ISBN

978-1-4244-4540-0

Type

conf

DOI

10.1109/NLPKE.2009.5313823

Filename

5313823