Morpheme Based Myanmar Word Segmenter
Journal Title: International Journal of Trend in Scientific Research and Development - Year 2019, Vol 3, Issue 5
Abstract
Myanmar script has no fixed delimiters between words or syllables. Therefore, to achieve meaningful and correct segmented words from the text is a challenging task. This paper has proposed a morpheme based Myanmar word tokenizer which combines rule based syllable breaking and dictionary lookup syllable merging methods with longest string matching approach. The proposed approach is tested on a Monolingual dictionary that contains useful information for the word segmentation. It also contains above 32,581 words including headwords, stop words and essential words with Myanmar3 font. These words are collected from Myanmar and Essential Words dictionaries. According to the experimental results, it can provide the promising segmentation accuracy of Myanmar text. Sin Thi Yar Myint | Hanni Htun | Myat Myo Nwe Wai "Morpheme Based Myanmar Word Segmenter" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-5 , August 2019, URL: https://www.ijtsrd.com/papers/ijtsrd26520.pdfPaper URL: https://www.ijtsrd.com/computer-science/other/26520/morpheme-based-myanmar-word-segmenter/sin-thi-yar-myint
Authors and Affiliations
Keywords
Related Articles
- EP ID EP628754
- DOI 10.31142/ijtsrd26520
- Views 75
- Downloads 0
Investigation of the Effect of Hall, Hall Constant and Density on Conductors Silver, Copper and Tungsten
Effect of Hall is the most applied issue in materials science. The purpose of this paper is to investigate the effect of Hall on conductive metals such as silver, copper, and tungsten. Dimensions of the copper sheet 83mm...
Approach of Herbal Drugs in Treatment of Cardio Vascular Disease
Herbs have been utilized as restorative medicines since the start of development and a few subsidiaries eg, headache medicine, reserpine, and digitalis have moved toward becoming pillars of human pharmacotherapy. For car...
Improving Analog Performance and Suppression of Subthreshold Swing using Hetero-Junction Less Double Gate Tunnel FETs
In this paper, we investigated a new device, Hetero-junction less (H-JL) Double Gate Tunnel Field Effect Transistors (DGTFET) with high-k. III-V semiconductor material (like InAs-Si) gives excellent performance when InAs...
Ensuring National Integration, Peace and Security in Nigeria through Qualitative Language Education
The thrust of this paper is to show how inappropriate use of language could threaten national integration, peace and security while appropriate use could enhance them. Plato believed that education should aim at producin...
Data Storing in Multitenant Clouds using Split and Merge Method
Resource Accounting of Shared IT Resources is a technique that distributes the excess dynamic local workload evenly across all the nodes. It is used for achieving a better service provisioning and resource utilization ra...