• Aug 23, 2021 News!Vol.10, No.3 has been published with online version.   [Click]
  • Aug 27, 2020 News!Welcome Prof. D. P. Sharma from India to join the Editorial board of IJFCC     [Click]
  • Aug 23, 2021 News!The papers published in No. 10, No. 3 have all received dois from Crossref.     [Click]
General Information

Prof. Pascal Lorenz
University of Haute Alsace, France
It is my honor to be the editor-in-chief of IJFCC. The journal publishes good papers in the field of future computer and communication. Hopefully, IJFCC will become a recognized journal among the readers in the filed of future computer and communication.

IJFCC 2021 Vol.10(2): 23-28 ISSN: 2010-3751
DOI: 10.18178/ijfcc.2021.10.2.575

Temporal Feature Aggregation for Text Classification Based on Ensembled Deep-Learning Models

Jiali Yu, Zhiliang Qin, Linghao Lin, Yu Qin, and Yingying Li
Abstract—In this paper, we focus on the text classification task, which is a most import task in the area of Natural Language Processing (NLP). We propose an innovative convolutional neural network (CNN) model to perform temporal feature aggregation (TFA) effectively, which has a highly representative capacity to extract sequential features from vectorized numerical embeddings. First, we feed embedded vectors into a bi-directional LSTM (Bi-LSTM) model to capture the contextual information of each word. Afterwards, we propose to use the state-of-the-art deep-learning models as key components of the architecture, i.e., the Xception model and the WaveNet model, to extract temporal features from deep convolutional layers concurrently. To facilitate an effective feature fusion, we concatenate the outputs of two component models before forwarding to a drop-out layer to alleviate over-fitting and subsequently a fully-connected dense layer to perform the final classification of input texts. Experiments demonstrate that the proposed method achieves performance comparable to the state-of-the-art models while at a significantly lower computational complexity. Our approach obtains the cross-validation score of 95.83% for the Quora Insincere Question Classification (QIQC) dataset, and the cross-validation score of 83.10% for the Spooky Author Identification (SAI) dataset, respectively, which are among the best published results. The proposed method can be readily generalized to signal processing tasks, e.g., environmental sound classification (ESC) and machine fault analysis (MFA).

Index Terms—NLP, text classification, word embedding, bi-LSTM, Xception, WaveNet.

The authors are with Weihai Beiyang Electric Group Co. Ltd., Weihai, Shandong, China (e-mails: {yujiali, qinzhiliang, linlinghao, qinyu, liyingying}@beiyang.com}; Corresponding author: Zhiliang Qin (qinzhiliang@beiyang.com)


Cite: Jiali Yu, Zhiliang Qin, Linghao Lin, Yu Qin, and Yingying Li, "Temporal Feature Aggregation for Text Classification Based on Ensembled Deep-Learning Models," International Journal of Future Computer and Communication vol. 10, no. 2, pp. 23-28, 2021.

Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Copyright © 2008-2021. International Journal of Future Computer and Communication. All rights reserved.
E-mail: ijfcc@ejournal.net