Automatic Template Generation for Myanmar Preposition Checking System

Abstract

Although the numbers of researches are increased in natural language processing, the development of grammar checking system for Myanmar language is very few. Much of the researches in checking area depends on hand-crafted rules and focuses on certain error types. However, the manual process of creation of rules is costly, time-consuming and error-prone. It seems therefore advisable to use machine-learning algorithms to create the rules automatically. In this paper, we describe a system for correcting Myanmar preposition errors automatically and non-native writers often make these errors. A decision tree algorithm (DT) is applied for automatic template generation of preposition errors using Myanmar Text Corpus. Correct Sentences in the corpus increase the performance of the method. The method works automatically, does not require problem domain expert to build these rule and can be applied to Myanmar language text.