Myanmar Homonym Disambiguation System

Abstract

Natural Language Processing (NLP) is one of the most important research areas in Human Language. One of the challenges in Natural Language Processing (NLP) is to resolve ambiguous homonyms or homonym errors in sentences. Myanmar Homonym Disambiguation System is the kind of Word Sense Disambiguation System in Natural Language Processing. This system is needed for Myanmar Word Segmentation and Spell Checker System. If the sentence contains incorrect homonyms, this sentence cannot be segmented correctly. Moreover, incorrect usage of homonyms is a common problem in Myanmar to English translation. In this paper, Myanmar Homonym Disambiguation System has been described. This system detects homonym errors or ambiguous homonyms and then resolves these errors by using Corpus-Based N-Gram Model. Myanmar Text Corpus is also needed in calculation of N-Gram Model for this system. After resolving homonym errors, the system will output the sentence with correct homonyms.