Ajou University repository

Gated Convolutional Neural Networks for Text Classification
Citations

SCOPUS

0

Citation Export

Publication Year
2021-01-01
Journal
Lecture Notes in Electrical Engineering
Publisher
Springer Science and Business Media Deutschland GmbH
Citation
Lecture Notes in Electrical Engineering, Vol.715, pp.309-316
Keyword
Convolutional neural networksGate mechanismText classification
Mesh Keyword
Invariant featuresLarge datasetsNAtural language processingRecurrent neural network (RNNs)Sentiment classificationState of the artText classificationTopic Classification
All Science Classification Codes (ASJC)
Industrial and Manufacturing Engineering
Abstract
The popular approach for several natural language processing tasks involves deep neural networks, and in particular, recurrent neural networks (RNNs) and convolutional neural networks (CNNs). While RNNs can capture the dependency in a sequence of arbitrary length, CNNs are suitable for extracting position-invariant features. In this study, a state-of-the-art CNN model incorporating a gate mechanism that is typically used in RNNs, is adapted to text classification tasks. The incorporated gate mechanism allows the CNNs to better select which features or words are relevant for predicting the corresponding class. Through experiments on various large datasets, it was found that the introduction of a gate mechanism into CNNs can improve the accuracy of text classification tasks such as sentiment classification, topic classification, and news categorization.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36662
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85101542520&origin=inward
DOI
https://doi.org/10.1007/978-981-15-9343-7_43
Journal URL
http://www.springer.com/series/7818
Type
Conference
Funding
Acknowledgements This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2019R1F1A1058548).
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Sohn, Kyung-Ah Image
Sohn, Kyung-Ah손경아
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.