Unsupervised Text Feature Learning via Deep Variational Auto-encoder

Authors

  • Genggeng Liu Fuzhou University
  • Lin Xie Fuzhou University
  • Chi-Hua Chen Fuzhou University

DOI:

https://doi.org/10.5755/j01.itc.49.3.25918

Keywords:

Machine learning, dimensionality reduction, text classification, variational auto-encoder, unsupervised feature learning

Abstract

Dimensionality reduction plays an important role in the data processing of machine learning and data mining, which makes the processing of high-dimensional data more efficient. Dimensionality reduction can extract the low-dimensional feature representation of high-dimensional data, and an effective dimensionality reduction method can not only extract most of the useful information of the original data, but also realize the function of removing useless noise. The dimensionality reduction methods can be applied to all types of data, especially image data. Although the supervised learning method has achieved good results in the application of dimensionality reduction, its performance depends on the number of labeled training samples. With the growing of information from internet, marking the data requires more resources and is more difficult. Therefore, using unsupervised learning to learn the feature of data has extremely important research value. In this paper, an unsupervised multilayered variational auto-encoder model is studied in the text data, so that the high-dimensional feature to the low-dimensional feature becomes efficient and the low-dimensional feature can retain mainly information as much as possible. Low-dimensional feature obtained by different dimensionality reduction methods are used to compare with the dimensionality reduction results of variational auto-encoder (VAE), and the method can be significantly improved over other comparison methods.

Author Biography

Chi-Hua Chen, Fuzhou University

Chi-Hua Chen is a distinguished professor (Minjiang scholar and Qishan scholar) for the College of Mathematics and Computer Science of Fuzhou University and a chair professor for the Navigation College of Dalian Maritime University. He received his B.S. degree from the Department of Management Information Systems of National Pingtung University of Science and Technology in 2007, a M.S. degree from the Institute of Information Management of National Chiao Tung University (NCTU) in 2009, and a Ph.D. degree from the Department of Information Management and Finance of NCTU in 2013. Furthermore, he served as an assistant professor for the Department of Industrial Engineering and Engineering Management of National Tsing Hua University, the Department of Information Management and Finance of NCTU, the Department of Transportation and Logistics Management of NCTU, the Department of Communication and Technology of NCTU, the Bachelor Degree Program of Digital Marketing of National Taipei University, and the Department of Information Management of National Kaohsiung University of Science and Technology. He also served as a research fellow for the Internet of Things Laboratory of Chunghwa Telecommunication Laboratories.
He has published over 270 journal articles, conference articles, and patents. He serves as the Guest Editor-in-Chief of the Special Issue on "Machine Learning and Deep Learning Methods for Wireless Network Applications" for the EURASIP Journal on Wireless Communications and Networking and a Guest Editor of the Special Issue on "Deep Learning Applications with Practical Measured Results in Electronics Industries" for the Electronics. He served as an Editor-in-Chief for the IEEE Technology and Engineering Education, a Guest Editor-in-Chief for the ISPRS International Journal of Geo-Information, a Guest Editor-in-Chief for the Symmetry, a Guest Editor-in-Chief for the Agronomy, a Guest Editor-in-Chief for the IEEE Multidisciplinary Engineering Education Magazine, and a Guest Editor for the Mathematical Problems in Engineering. He is also currently serving as a member of the editorial boards of several international journals (e.g. IEEE Access, Information Technology and Control, etc.). His recent research interests include Internet of things, big data, deep learning, cloud computing, cellular networks, data mining, intelligent transportation systems, network security, healthcare systems, augmented reality, e-learning systems, and digital marketing. He is a senior member (M'17─SM'19) of IEEE and a member of ACM.

Downloads

Published

2020-09-28

Issue

Section

Articles