https://ph05.tci-thaijo.org/index.php/JIIST <p>We sincerely apologize for the incompleteness of the website's content. We are in the process of transferring information from the old website to this website. However, you can submit articles for publication with us on this website system as usual. Thank you for your understanding.</p> <p> </p> <p>Journal of Intelligent Informatics and Smart Technology aims to be a publisher of a wide range of high quality academic journals such as original articles, review article, short communication, and case report in the field of artificial intelligence including Natural Language Processing, Speech Recognition, Machine Learning, Image Processing, Robotics, Semantic Web, Intelligent Computer-Aided Instruction (ICAI), Expert Systems, and other related-fields.</p> <p>The articles are all published in English.</p> Artificial Intelligence Association of Thailand en-US Journal of Intelligent Informatics and Smart Technology 2586-9167 https://ph05.tci-thaijo.org/index.php/JIIST/article/view/87 <p>&nbsp;A sentence is an independent unit which is a string of complete words containing valuable information of the text. In informal Myanmar Language, for which most of NLP applications like Automatic Speech Recognition (ASR) are used, there is no predefined rule to mark the end of sentence. In this paper, we contributed the first corpus for Myanmar Sentence Segmentation and proposed the first systematic study with Machine Learning based Sequence Tagging as baseline and Neural Machine Translation approach. Before conducting the experiments, we prepared two types of data - one containing only sentences and the other containing both sentences and paragraphs. We trained each model on both types of data and evaluated the results on both types of test data. The accuracies were measured in terms of Bilingual Evaluation Understudy (BLEU) and character n-gram F-score (CHRF ++) scores. Word Error Rate (WER) was also used for the detailed study of error analysis. The experimental results show that Sequence-to-Sequence architecture based Neural Machine Translation approach with the best BLEU score (99.78), which is trained on both sentence-level and paragraph-level data, achieved better CHRF ++ scores (+18.4) and (+16.7) than best results of such machine learning models on both test data.</p> Thura Aung Ye Kyaw Thu Zar Zar Hlaing Copyright (c) 2023 Journal of Intelligent Informatics and Smart Technology 2023-11-17 2023-11-17 e001 e001