Comparative Study of Naïve Bayesian Classifier and Transformation - Based Learning for Myanmar Function Tagging

This paper describes the use of two machine learning techniques, Naive Bayesian classifier (NB) and transformation-based learning (TBL), to address the task of assigning function tags to Myanmar sentences. Function tagging is a process of assigning syntactic categories like subject, object, time and location to each word in the text document. It is an important step in Natural Language Processing. Function tags can help to improve the performance of Myanmar to English machine translation system. In this paper, we present a comparison of two methods in our experiments. The results showed that TBL was better and outperformed NB and there was a slight difference between the results. Keywords— Naïve Bayesian, transformation-based learning, function tagging, Myanmar sentences