A PLM-LCN Network-Based Model for e-Library Automatic Classification

Efficient and accurate categorization of Chinese books in digital libraries is still a challenge, and traditional manual methods are difficult to cope with the huge number of books. In this study, a novel Chinese book classification model based on an enhanced BERT architecture is proposed, which con...

Full description

Saved in:
Bibliographic Details
Main Authors: Ke Lu, Bei Zheng, Jingjing Shi
Format: Article
Language:English
Published: Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek 2025-01-01
Series:Tehnički Vjesnik
Subjects:
Online Access:https://hrcak.srce.hr/file/478045
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Efficient and accurate categorization of Chinese books in digital libraries is still a challenge, and traditional manual methods are difficult to cope with the huge number of books. In this study, a novel Chinese book classification model based on an enhanced BERT architecture is proposed, which contains a pre-trained language model (PLM) and a long-short-time convolutional neural network (LCN) for improved feature extraction. Experimental results showed that the model achieved up to 93.6% for Micro F1, 95.3% for Macro F1, 90% for Mac-P, and 91% for Mic-P with an input text length of 256 and a batch size of 32. The results illustrate the model's efficacy in Chinese book classification, offering theoretical advancements in natural language processing applications and practical enhancements in library resource management and user services.
ISSN:1330-3651
1848-6339