Checking the Correctness of Bangla Words using N-Gram

N-gram model is used in many domains like spelling and syntactic verification, speech recognition, machine translation, character recognition and like others. This paper describes a system for checking the correctness of a bangle word using Ngram model. An experimental corpus containing one million word tokens was used to train the system. The corpus was a part of the BdNC01 corpus, created in the SIPL lab. of Islamic university. Collecting several sample text from different newspapers, the system was tested by 50,000 correct and another 50,000 incorrect words. The system has successfully detected the correctness of the test words at a rate of 96.17%. This paper also describes the limitations of the system with possible solutions. General Terms Artificial Intelligence, Natural Language Processing