Naïve Bayes for Function Tagging in Myanmar Language

Abstract

This paper proposes an approach to annotate function tags for unparsed text. We address the question of whether data-driven function tag assignment method can be applied to Myanmar language. We assign function tags directly basing on lexical information, which is easily scalable for languages that lack sufficient parsing resources or have inherent linguistic challenges for parsing. We investigate a supervised sequence learning method to automatically recognize function tags. In order to demonstrate the effectiveness and versatility of our method, we investigate function tag assignment for unparsed text by applying Naïve Bayesian theory. Our approach to functional analysis is to classify, so far as possible, all the processes and states which languages must describe, and to identify the functional elements which are needed for each one to construct a meaningful sentence.