2026-06-16T09:35:39Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/4614 2022-03-24T23:12:44Z 1582963302567:1597824175385 user-ucsy

Improving accuracy of part-of-speech (POS) tagging using hidden markov model and morphological analysis for Myanmar language Cing, Dim Lam Soe, Khin Mar In Natural Language Processing (NLP), Word segmentation and Part-ofSpeech (POS) tagging are fundamental tasks. The POS information is alsonecessary in NLP’s preprocessing work applications such as machinetranslation (MT), information retrieval (IR), etc. Currently, there are manyresearch efforts in word segmentation and POS tagging developed separatelywith different methods to get high performance and accuracy. For MyanmarLanguage, there are also separate word segmentors and POS taggers based onstatistical approaches such as Neural Network (NN) and Hidden MarkovModels (HMMs). But, as the Myanmar language's complex morphologicalstructure, the OOV problem still exists. To keep away from error and improvesegmentation by utilizing POS data, segmentation and labeling should bepossible at the same time.The main goal of developing POS tagger for anyLanguage is to improve accuracy of tagging and remove ambiguity insentences due to language structure. This paper focuses on developing wordsegmentation and Part-of- Speech (POS) Tagger for Myanmar Language. Thispaper presented the comparison of separate word segmentation and POStagging with joint word segmentation and POS tagging. 2020-04 http://hdl.handle.net/20.500.12678/0000004614 https://meral.edu.mm/records/4614