Research on Policy Tools Classification Based on ChatGPT Augmentation and Supervised Contrastive Learning

被引：0
|
作者：
Hu, Zhiqiang [1 ]
Li, Pengjun [1 ]
Wang, Jinlong [1 ]
Xiong, Xiaoyun [1 ]
机构：
[1] School of Information and Control Engineering, Qingdao University of Technology, Shandong, Qingdao,266525, China
来源：
Computer Engineering and Applications | 2024年 / 60卷 / 07期
关键词：
The classification of policy tools is an important dimension in the quantification and analysis of policy texts. Due to the scarcity of training data; models are prone to overfitting; resulting in reduced prediction confidence and an increased risk of misclassification. Therefore; policy tool classification method based on ChatGPT augmentation and supervised contrastive learning is proposed. The method consists of two stages: pre-training language model fine-tuning and ChatGPT decision augmentation. In the first stage; ChatGPT; a large language model; augments policy texts to increase the training dataset; while supervised contrastive learning fine-tune the RoBERTa model to improve classification performance. In the second stage; ChatGPT assists in the decision-making process for low confidence texts through the pretrained language model and reduces the risk of misclassifying similar texts. Experiments on the digital industry policy tools classification dataset and the Tnews dataset show that the proposed method surpasses mainstream research approaches and can effectively improve the performance of the base model; with a more significant improvement observed when the training samples are limited. © 2024 Journal of Computer Engineering and Applications Beijing Co; Ltd; Science Press. All rights reserved;
D O I：
10.3778/j.issn.1002-8331.2308-0354
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：292 / 305
相关论文
共 50 条
  • [31] Attention decoupled contrastive learning for semi-supervised segmentation method based on data augmentation
    Pan, Pan
    Chen, Houjin
    Li, Yanfeng
    Peng, Wanru
    Cheng, Lin
    PHYSICS IN MEDICINE AND BIOLOGY, 2024, 69 (12):
  • [32] FedFAME: A Data Augmentation Free Framework based on Model Contrastive Learning for Federated Semi-Supervised Learning
    Malaviya, Shubham
    Shukla, Manish
    Korat, Pratik
    Lodha, Sachin
    38TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2023, 2023, : 1114 - 1121
  • [33] ChatGPT and Generative AI Tools for Learning and Research
    Kim, Bohyun
    Computers in Libraries, 2023, 43 (06) : 41 - 42
  • [34] ChatGPT based contrastive learning for radiology report summarization
    Luo, Zhenjie
    Jiang, Zuowei
    Wang, Mingyang
    Cai, Xiaoyan
    Gao, Dehong
    Yang, Libin
    EXPERT SYSTEMS WITH APPLICATIONS, 2025, 267
  • [35] Research on Personalized AEB Strategies Based on Self-Supervised Contrastive Learning
    Li, Haotian
    Jin, Hui
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 25 (02) : 1303 - 1316
  • [36] Research on Text Sentiment Semantic Optimization Method Based on Supervised Contrastive Learning
    Xiong, Shuchu
    Li, Xuan
    Wu, Jiani
    Zhou, Zhaohong
    Meng, Han
    Data Analysis and Knowledge Discovery, 2024, 8 (06) : 69 - 81
  • [37] SWIN transformer based contrastive self-supervised learning for animal detection and classification
    Agilandeeswari, L.
    Meena, S. Divya
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (07) : 10445 - 10470
  • [38] Classification of Ground-Based Cloud Images by Contrastive Self-Supervised Learning
    Lv, Qi
    Li, Qian
    Chen, Kai
    Lu, Yao
    Wang, Liwen
    REMOTE SENSING, 2022, 14 (22)
  • [39] Occluded Scene Classification via Cascade Supervised Contrastive Learning
    Xu, Jianming
    Li, Yunfei
    Shi, Qian
    He, Lin
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 4565 - 4578
  • [40] Attention-based supervised contrastive learning on fine-grained image classification
    Li, Qian
    Wu, Weining
    PATTERN ANALYSIS AND APPLICATIONS, 2024, 27 (03)
12345