Joint Word Segmentation and Part-of-Speech (POS) Tagging for Myanmar Language

Abstract

In natural language processing (NLP), Word segmentation and Part-of-Speech (POS) tagging are fundamental tasks. The POS information is also necessary in NLP- based applications such as machine translation (MT), information retrieval (IR), etc. Currently, there are many research efforts in word segmentation and POS tagging developed separately with various approaches to reach high performance and accuracy. For Myanmar Language, there are also separate word segmentors and POS taggers based on statistical approaches such as Neural Network (NN) and Hidden Markov Models (HMMs). However, the Myanmar language has the complex morphological structure and the Out-of-Vocabulary (OOV) problem still exists. Thus, this paper proposed morphological analysis based joint Myanmar word segmentation and POS tagging using Hidden Markov Models (HMM) and morphological rules. This paper has also presented the comparison of accuracy result using HMM only, and HMM with morphological analysis.