2026-06-26T21:43:05Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/3450 2021-12-13T00:34:16Z 1582963302567:1597824273898 user-ucsy

Clustering Analogous Words in Myanmar Language using Word Embedding Model Mon, Aye Myat Soe, Khin Mar Word embedding represents the words in terms ofvectors. It is influenced on different NLP researchareas such as document classification, authoridentification, sentiment analysis, etc. One of themost popular embedding models is Word2Vec model.It provides efficient representations of words by usingContinuous Bag of Words model (CBOW) and SkipGram model. In English language, word embeddingmodel can be applied for data preprocessing well butthere is a very little amount of work done inMyanmar language. Text preprocessing is importantpart to build embedding model and it is asignificantly effect on final results. This paper tries toextract the analogous words between Myanmar newsarticles focus on the bag of words (CBOW) modelusing different features vector sizes. By analyzingword embedding model are obtained the betterresults with a high dimensional vectors than a lowdimensional vectors to cluster the words based on itsrelatedness. 2019-02-27 http://hdl.handle.net/20.500.12678/0000003450 https://meral.edu.mm/records/3450