Automatic correction of typos in the typed texts is one of the goals of research in artificial intelligence, data mining and natural language processing. Most of the existing methods are based on searching in dictionaries and determining the similarity of the dictionary entries and the given word. This paper presents the design, implementation, and evaluation of a Farsi typo correction system using the Hopfield and multilayer perceptron (MLP) neural networks.The results show that for learning a dictionary of 4 to 256 words of 4 to 6 characters, the correction accuracy of the Hopfield network is 55% to 100% and for the multilayer perceptron 80% to 100%. The hybrid network can achieve a correction accuracy of 80% to 100% for over 3000 words.
Rights and permissions | |
This Journal is an open access Journal Licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. (CC BY NC 4.0) |