Tribhuvan University, Institute of Engineering, Thapathali Campus
UGC Nepal accreditation badge
Accredited by UGC NepalUniversity Grants CommissionQuality Education Since 1967 A.D.

Efficient Estimation of Nepali Word Representations in Vector Space

Thumbnail Image

Files

Efficient-Estimation-of-Nepali-Word-Representations-in-Vector-Space.pdf (553.01 KB)Download

Date

2020-03-31

Authors





Journal Title

Journal ISSN

Volume Title

Publisher

Thapathali Campus, Institute of Engineering, Tribhuvan University

DOI

10.3126/jiee.v3i1.34327

Abstract

Word representation is a means of representing a word as mathematical entities that can be read, reasoned and manipulated by computational models. The representation is required for input to any new modern data models and in many cases, the accuracy of a model depends on it. In this paper, we analyze various methods of calculating vector space for Nepali words and postulate a word to vector model based on the Skip-gram model with NCE loss capturing syntactic and semantic word relationships. This is an attempt to implement a paper by Mikolov on Nepali words.

Description

Journal: Journal of Innovations in Engineering Education (JIEE), ISSN 2594-343X (print), 2773-823X (online) Volume/Issue: Vol. 3, Issue 1 (2020), pages 71-77 Article type: Research Article Published: 2020-03-31 DOI: https://doi.org/10.3126/jiee.v3i1.34327 Authors and affiliations: - Janardan Bhatta (Thapathali Campus, Institute of Engineering, Tribhuvan University, Kathmandu, Nepal) - Dipesh Shrestha (Thapathali Campus, Institute of Engineering, Tribhuvan University, Kathmandu, Nepal) - Santosh Nepal (Thapathali Campus, Institute of Engineering, Tribhuvan University, Kathmandu, Nepal) - Saurav Pandey (Thapathali Campus, Institute of Engineering, Tribhuvan University, Kathmandu, Nepal) - Shekhar Koirala (Thapathali Campus, Institute of Engineering, Tribhuvan University, Kathmandu, Nepal) TCIOE department(s): Department of Electronics and Computer Engineering Publisher: Thapathali Campus, Institute of Engineering, Tribhuvan University License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0), https://creativecommons.org/licenses/by-nc-nd/4.0/ Journal website: https://journal.tcioe.edu.np/articles/2629156a-387a-42a7-85a0-8bf6525ede60 NepJOL: https://www.nepjol.info/index.php/jiee/article/view/34327

Keywords

CBOW , NCE loss , One Hot Encoding , Skip-gram , TF-IDF , Word2Vec , JIEE , Journal of Innovations in Engineering Education , JIEE 2020 , JIEE Volume 3 , Research Article , Thapathali Campus , TCIOE , Institute of Engineering , IOE , Tribhuvan University , Nepal , engineering research Nepal , peer-reviewed journal article , open access , Department of Electronics and Computer Engineering

Citation

Bhatta, J., Shrestha, D., Nepal, S., Pandey, S., & Koirala, S. (2020). Efficient Estimation of Nepali Word Representations in Vector Space. Journal of Innovations in Engineering Education, 3(1), 71-77. https://doi.org/10.3126/jiee.v3i1.34327

URI

https://elibrary.tcioe.edu.np/handle/123456789/264

Collections

Journal of Thapathali Campus
Faculty Publications

Endorsement

Review

Supplemented By

Referenced By

Creative Commons license

Copyright (c) 2020 JIEE and the authors. Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).
Except where otherwise noted, this item's license is described as Copyright (c) 2020 JIEE and the authors. Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).