Text classification methods based on knowledge graph and BERT

Jiang Ke; Peng Cheng

doi:10.1117/12.2692602

23 August 2023 Text classification methods based on knowledge graph and BERT

Jiang Ke, Peng Cheng

Proceedings Volume 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023); 127842W (2023) https://doi.org/10.1117/12.2692602
Event: 2023 2nd International Conference on Applied Statistics, Computational Mathematics and Software Engineering (ASCMSE 2023), 2023, Kaifeng, China

Abstract

The problem of text classification based on natural language processing has become a research hotspot, but the current text classification faces the problems of difficult extraction of key elements, fuzzy classification features and overlapping labels, and the commonly used text classification methods may have poor classification results. This article proposes classification studies for models that combine knowledge graph with the BERT model. The experimental results show that the K-BERT model incorporating knowledge graph achieves 88.2% correct classification rate on court verdicts, which is about 5% higher compared with the BERT model, which means that the model in this paper can improve the correct rate of text classification to a certain extent.

Citation Download Citation

Jiang Ke and Peng Cheng "Text classification methods based on knowledge graph and BERT", Proc. SPIE 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023), 127842W (23 August 2023); https://doi.org/10.1117/12.2692602

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available