Myanmar Word Segmentation Using Hybrid Approach
Khine Myint Myat, Khin Mar Soe · 2019
Word segmentation is a basic task and an important problem in naturallanguage processing. In Myanmar language, words composed of single or multiplesyllables are usually not separated by white space. Myanmar word segmentation is todetermine the boundaries of words for languages without word separators inorthography. This system uses a 2-step longest matching approach. The first step wassyllable segmentation and second uses Hybrid Approach of left-to-right syllablemaximum matching and hierarchical expectation maximization approach. This systemis intended to be able to use as a pre-processing tool in Myanmar text processing suchas Machine Translation, Information Retrieval, Search Engine using Myanmarlanguage. The experimental result shows 93% of accuracy based on a collection of300 articles from the business, entertainment and sports sections of the Myanmarnewspaper nearly 35,000 words. The proposed word segmentation is implemented asa web-based tool using C# .Net language.