MDCNN: Multi-Teacher Distillation-Based CNN for News Text Classification

News text classification is crucial for efficient information acquisition and dissemination. While deep learning models, such as BERT and BiGRU, excel in accuracy for text classification, their high complexity and resource demands hinder practical deployment. To address these challenges, we proposed...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaolei Guo, Qingyang Liu, Yanrong Hu, Hongjiu Liu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10943179/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849702129874239488
author Xiaolei Guo
Qingyang Liu
Yanrong Hu
Hongjiu Liu
author_facet Xiaolei Guo
Qingyang Liu
Yanrong Hu
Hongjiu Liu
author_sort Xiaolei Guo
collection DOAJ
description News text classification is crucial for efficient information acquisition and dissemination. While deep learning models, such as BERT and BiGRU, excel in accuracy for text classification, their high complexity and resource demands hinder practical deployment. To address these challenges, we proposed MDCNN (Multi-teacher Distillation-based CNN), which leverages knowledge distillation with BERT and BiGRU as teacher models and TextCNN as the student model. Experiments on three benchmark news dataset demonstrate that MDCNN improves classification accuracy by nearly 2% while significantly reducing computational overhead, offering a practical solution for real-world applications.
format Article
id doaj-art-c30d99f97ec34c85a62ace484a73c2f9
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c30d99f97ec34c85a62ace484a73c2f92025-08-20T03:17:44ZengIEEEIEEE Access2169-35362025-01-0113566315664110.1109/ACCESS.2025.355522410943179MDCNN: Multi-Teacher Distillation-Based CNN for News Text ClassificationXiaolei Guo0https://orcid.org/0009-0001-1390-1479Qingyang Liu1https://orcid.org/0000-0003-0491-3248Yanrong Hu2https://orcid.org/0000-0002-9826-5212Hongjiu Liu3https://orcid.org/0000-0001-8175-264XCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaInstitute of Informatics, Georg-August-Universität Göttingen, Göttingen, GermanyCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaNews text classification is crucial for efficient information acquisition and dissemination. While deep learning models, such as BERT and BiGRU, excel in accuracy for text classification, their high complexity and resource demands hinder practical deployment. To address these challenges, we proposed MDCNN (Multi-teacher Distillation-based CNN), which leverages knowledge distillation with BERT and BiGRU as teacher models and TextCNN as the student model. Experiments on three benchmark news dataset demonstrate that MDCNN improves classification accuracy by nearly 2% while significantly reducing computational overhead, offering a practical solution for real-world applications.https://ieeexplore.ieee.org/document/10943179/Text classificationknowledge distillationBERTBiGRUTextCNN
spellingShingle Xiaolei Guo
Qingyang Liu
Yanrong Hu
Hongjiu Liu
MDCNN: Multi-Teacher Distillation-Based CNN for News Text Classification
IEEE Access
Text classification
knowledge distillation
BERT
BiGRU
TextCNN
title MDCNN: Multi-Teacher Distillation-Based CNN for News Text Classification
title_full MDCNN: Multi-Teacher Distillation-Based CNN for News Text Classification
title_fullStr MDCNN: Multi-Teacher Distillation-Based CNN for News Text Classification
title_full_unstemmed MDCNN: Multi-Teacher Distillation-Based CNN for News Text Classification
title_short MDCNN: Multi-Teacher Distillation-Based CNN for News Text Classification
title_sort mdcnn multi teacher distillation based cnn for news text classification
topic Text classification
knowledge distillation
BERT
BiGRU
TextCNN
url https://ieeexplore.ieee.org/document/10943179/
work_keys_str_mv AT xiaoleiguo mdcnnmultiteacherdistillationbasedcnnfornewstextclassification
AT qingyangliu mdcnnmultiteacherdistillationbasedcnnfornewstextclassification
AT yanronghu mdcnnmultiteacherdistillationbasedcnnfornewstextclassification
AT hongjiuliu mdcnnmultiteacherdistillationbasedcnnfornewstextclassification