Deep Learning Based Robust Text Classification Method via Virtual Adversarial Training

Deep Learning Based Robust Text Classification Method via Virtual Adversarial Training

The existing methods of generating adversarial texts usually change the original meanings of texts significantly and even generate the unreadable texts. These less readable adversarial texts can misclassify the machine classifier successfully, but they cannot deceive the human observers very well. I...

Full description

Bibliographic Details
Main Authors: Wei Zhang, Qian Chen, Yunfang Chen
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Adversarial training
model interpretation
text classification
deep learning
Online Access:https://ieeexplore.ieee.org/document/9040544/

Internet

https://ieeexplore.ieee.org/document/9040544/

Similar Items