The Library
Text classification based on conditional reflection
Tools
Jin, Yanliang, Luo, Can, Guo, Weisi, Xie, Jinfei, Wu, Dijia and Wang, Rui (2019) Text classification based on conditional reflection. IEEE Access . doi:10.1109/ACCESS.2019.2921976 ISSN 2169-3536.
|
PDF
WRAP-text-classification-based-conditional-reflection-Guo-2019.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (850Kb) | Preview |
Official URL: http://doi.org/10.1109/ACCESS.2019.2921976
Abstract
Text classification is an essential task in many Natural Language Processing (NLP) applications, we know each sentence may have only a few words that play an important role in text classification, whilst other words have no significant effect on the classification results. Finding these keywords has an important impact on the classification accuracy. In this paper, we propose a network model, named RCNNA (Recurrent Convolution Neural Networks with Attention), which models on the human conditional reflexes for text classification. The model combines bidirectional LSTM (BLSTM), attention mechanism and Convolutional Neural Networks (CNN) as the receptors, nerve centers and effectors in the reflex arc. The receptors get the context information through BLSTM, the nerve centers get the important information of the sentence through the attention mechanism. And the effectors capture more key information by CNN. Finally, the model outputs the classification result by the softmax function. We test our NLP algorithm on four datasets containing Chinese and English for text classification, including a comparison of random initialization word vectors and pre-training word vectors. Experiments show that RCNNA achieves the best performance by comparing with state-of-the-art baseline methods.
Item Type: | Journal Article | ||||||||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software | ||||||||||||||||||||||||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > Engineering | ||||||||||||||||||||||||||||||
Library of Congress Subject Headings (LCSH): | Natural language processing (Computer science), Neural networks (Computer science) | ||||||||||||||||||||||||||||||
Journal or Publication Title: | IEEE Access | ||||||||||||||||||||||||||||||
Publisher: | IEEE | ||||||||||||||||||||||||||||||
ISSN: | 2169-3536 | ||||||||||||||||||||||||||||||
Official Date: | 10 June 2019 | ||||||||||||||||||||||||||||||
Dates: |
|
||||||||||||||||||||||||||||||
DOI: | 10.1109/ACCESS.2019.2921976 | ||||||||||||||||||||||||||||||
Status: | Peer Reviewed | ||||||||||||||||||||||||||||||
Publication Status: | Published | ||||||||||||||||||||||||||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||||||||||||||||||||||||||
Date of first compliant deposit: | 12 June 2019 | ||||||||||||||||||||||||||||||
Date of first compliant Open Access: | 12 June 2019 | ||||||||||||||||||||||||||||||
RIOXX Funder/Project Grant: |
|
||||||||||||||||||||||||||||||
Open Access Version: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year