A probabilistic model for spelling correction

Authors

  • Lucian Sasu Transilvania University of Brasov, Romania

Keywords:

Spell correction, Levenshtein distance, Damerau-Levenshtein distance, Bayesian decision theory, restricted edit distance

Abstract

Spelling correctors are widely encountered in computer software applications and they provide the most plausible replacements for words that are presumably incorrect. The paper proposes a spelling correction method starting from the Damerau-Levenshtein edit distance and using Bayesian decision theory. The resulted algorithm is tested on a bag of words from the New York Times news articles.

Author Biography

Lucian Sasu, Transilvania University of Brasov, Romania

Faculty of Mathematics and Informatics

Downloads

Published

2011-07-26

Issue

Vol. 4(53) No. 1 (2011)

Section

INFORMATICS