Self-Adaptive Semantics Masking for Text Classification

Text classification is a typical problem in NLP, which is to classify a given text into a certain category. In this article, we propose a classification-based training method, which is mainly based on the input text adaptive masking, and then further pre-training and fine-tuning training. This train...

Full description

Saved in:
Bibliographic Details
Published in2021 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) pp. 390 - 394
Main Authors Zhang, Jinfan, Wu, Jiawei, Zhang, Hao
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2021
Subjects
Adaptation models
Artificial intelligence
Automation
masking
pretrained language model
Semantics
Text categorization
text classification
Training
Online AccessGet full text

Cover

More Information
Summary:Text classification is a typical problem in NLP, which is to classify a given text into a certain category. In this article, we propose a classification-based training method, which is mainly based on the input text adaptive masking, and then further pre-training and fine-tuning training. This training method makes it easier to obtain the semantic features of the text, and thus can improve the semantic learning ability of the model, and thus can improve the classification effect. Experiments show that compared with other classic methods, this method can now improve the classification performance.
DOI:10.1109/AIEA53260.2021.00088