Effective Spell Checking Methods Using Clustering Algorithms

Abstract

This paper presents a novel approach to spell checking using dictionary clustering. The main goal is to reduce the number of times distances have to be calculated when finding target words for misspellings. The method is unsupervised and combines the application of anomalous pattern initialization and partition around medoids (PAM). To evaluate the method, we used an English misspelling list compiled using real examples extracted from the Birkbeck spelling error corpus.