Nepali Text Document Classification Using Deep Neural Network

Authors

  • Sanjeev Subba Central Department of Computer Science and IT, Trubhuvan University
  • Nawaraj Paudel Central Department of Computer Science and IT, Tribhuvan University
  • Tej Bahadur Shahi Central Department of Computer Science and IT, Tribhuvan University

DOI:

https://doi.org/10.3126/tuj.v33i1.28677

Keywords:

Neural Network, Text Classification, Bag of words, Deep Learning, Machine Learning

Abstract

 An automated text classification is a well-studied problem in text mining which generally demands the automatic assignment of a label or class to a particular text documents on the basis of its content. To design a computer program that learns the model form training data to assign the specific label to unseen text document, many researchers has applied deep learning technologies. For Nepali language, this is first attempt to use deep learning especially Recurrent Neural Network (RNN) and compare its performance to traditional Multilayer Neural Network (MNN). In this study, the Nepali texts were collected from online News portals and their pre-processing and vectorization was done. Finally deep learning classification framework was designed and experimented for ten experiments: five for Recurrent Neural Network and five for Multilayer Neural Network. On comparing the result of the MNN and RNN, it can be concluded that RNN outperformed the MNN as the highest accuracy achieved by MNN is 48 % and highest accuracy achieved by RNN is 63%.

Downloads

Download data is not yet available.
Abstract
578
pdf
657

Author Biographies

Sanjeev Subba, Central Department of Computer Science and IT, Trubhuvan University

Master’s student

Nawaraj Paudel, Central Department of Computer Science and IT, Tribhuvan University

Lecturer

Tej Bahadur Shahi, Central Department of Computer Science and IT, Tribhuvan University

Lecturer

Downloads

Published

2019-06-30

How to Cite

Subba, S., Paudel, N., & Shahi, T. B. (2019). Nepali Text Document Classification Using Deep Neural Network. Tribhuvan University Journal, 33(1), 11–22. https://doi.org/10.3126/tuj.v33i1.28677

Issue

Section

Articles