2026-04-15T18:28:11Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/4338 2021-12-13T03:28:15Z 1582963302567:1597824273898 user-ucsy

A Comparison of Naïve Bayesian and Nearest Neighbor Cosine Classifiers for Myanmar Word Sense Disambiguation Aung, Nyein Thwet Thwet Soe, Khin Mar Thein, Ni Lar This paper presents Word SenseDisambiguation for Myanmar Language.Word Sense Disambiguation (WSD) is anintermediate but an important step in NaturalLanguage processing. WSD is defined as thetask of finding the correct sense of a word ina specific context.WSD systems can help toimprove the performance of statisticalmachine translation (MT) system. In the mostused classifiers, Nearest Neighbor Cosine(NNC) model has excellent performance, andNaïve Bayesian (NB) is preferred byresearchers for it is simple and useful. In thispaper, we choose NNC and NB as classifiersto disambiguate ambiguous Myanmar wordswith part-of-speech ‘noun’, ‘verb’ and‘adjective’. The WSD module developed herewill be used as a complement to improveMyanmar-English machine translationsystem. As an advantage, the system canimprove the accuracy of Myanmar to Englishlanguage translation. We present acomparison of two methods in ourexperiments. 2012-02-28 http://hdl.handle.net/20.500.12678/0000004338 https://meral.edu.mm/records/4338