2026-05-01T10:32:00Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/3376 2021-12-13T06:04:25Z 1582963302567:1597824273898 user-ucsy

Assigning automatically Part-of-Speech tags to build tagged corpus for Myanmar language Myint, Phyu Hninn A variety of Natural Language Processing (NLP)tasks, such as named entity recognition, stemming,question answering and machine translation, benefitfrom knowledge of the words syntactic categories orPart-of-Speech (POS). POS taggers must besuccessfully applied to assign a single best POS toevery word in a corpus.This paper presents to developPart-of-Speech tagged text corpora by employingBigram part-of-speech tagger. POS tagging is aprocess of assigning appropriate syntactic categoriesto each word in a sentence. As applying bigram modelfor automated tagging process we have provided anadequate annotated corpus from scratch. We have usedcustomized POS tagset to annotate the words in aMyanmar sentence. Our Bigram tagger has twophases: training with Hidden Markov Models (HMM)and decoding with Viterbi algorithm. 2010-12-16 http://hdl.handle.net/20.500.12678/0000003376 https://meral.edu.mm/records/3376