CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification
This paper introduces an extremely lightweight (with just over around two hundred thousand parameters) and computationally efficient CNN architecture, named CharTeC-Net (Character-based Text Classification Network), for character-based text classification problems. This new architecture is composed...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Journal of Electrical and Computer Engineering |
| Online Access: | http://dx.doi.org/10.1155/2020/9701427 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849434648204017664 |
|---|---|
| author | Aboubakar Nasser Samatin Njikam Huan Zhao |
| author_facet | Aboubakar Nasser Samatin Njikam Huan Zhao |
| author_sort | Aboubakar Nasser Samatin Njikam |
| collection | DOAJ |
| description | This paper introduces an extremely lightweight (with just over around two hundred thousand parameters) and computationally efficient CNN architecture, named CharTeC-Net (Character-based Text Classification Network), for character-based text classification problems. This new architecture is composed of four building blocks for feature extraction. Each of these building blocks, except the last one, uses 1 × 1 pointwise convolutional layers to add more nonlinearity to the network and to increase the dimensions within each building block. In addition, shortcut connections are used in each building block to facilitate the flow of gradients over the network, but more importantly to ensure that the original signal present in the training data is shared across each building block. Experiments on eight standard large-scale text classification and sentiment analysis datasets demonstrate CharTeC-Net’s superior performance over baseline methods and yields competitive accuracy compared with state-of-the-art methods, although CharTeC-Net has only between 181,427 and 225,323 parameters and weighs less than 1 megabyte. |
| format | Article |
| id | doaj-art-e9c7b00602e94dc3bbb5c73cc839920b |
| institution | Kabale University |
| issn | 2090-0147 2090-0155 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Electrical and Computer Engineering |
| spelling | doaj-art-e9c7b00602e94dc3bbb5c73cc839920b2025-08-20T03:26:34ZengWileyJournal of Electrical and Computer Engineering2090-01472090-01552020-01-01202010.1155/2020/97014279701427CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text ClassificationAboubakar Nasser Samatin Njikam0Huan Zhao1School of Information Science and Engineering, Hunan University, 057 Changsha, HN 410082, ChinaSchool of Information Science and Engineering, Hunan University, 057 Changsha, HN 410082, ChinaThis paper introduces an extremely lightweight (with just over around two hundred thousand parameters) and computationally efficient CNN architecture, named CharTeC-Net (Character-based Text Classification Network), for character-based text classification problems. This new architecture is composed of four building blocks for feature extraction. Each of these building blocks, except the last one, uses 1 × 1 pointwise convolutional layers to add more nonlinearity to the network and to increase the dimensions within each building block. In addition, shortcut connections are used in each building block to facilitate the flow of gradients over the network, but more importantly to ensure that the original signal present in the training data is shared across each building block. Experiments on eight standard large-scale text classification and sentiment analysis datasets demonstrate CharTeC-Net’s superior performance over baseline methods and yields competitive accuracy compared with state-of-the-art methods, although CharTeC-Net has only between 181,427 and 225,323 parameters and weighs less than 1 megabyte.http://dx.doi.org/10.1155/2020/9701427 |
| spellingShingle | Aboubakar Nasser Samatin Njikam Huan Zhao CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification Journal of Electrical and Computer Engineering |
| title | CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification |
| title_full | CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification |
| title_fullStr | CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification |
| title_full_unstemmed | CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification |
| title_short | CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification |
| title_sort | chartec net an efficient and lightweight character based convolutional network for text classification |
| url | http://dx.doi.org/10.1155/2020/9701427 |
| work_keys_str_mv | AT aboubakarnassersamatinnjikam chartecnetanefficientandlightweightcharacterbasedconvolutionalnetworkfortextclassification AT huanzhao chartecnetanefficientandlightweightcharacterbasedconvolutionalnetworkfortextclassification |