ALBERT-Driven Ensemble Learning for Medical Text Classification

Authors
  • Yiru Cang

  • Wangying Yang

  • Dan Sun

  • Zhi Ye

  • Zitao Zheng

Abstract

Health queries, as a specialized form of medical text, present unique challenges due to the presence of complex medical terminology, abbreviations, and linguistic features such as synonyms, antonyms, and polysemy. Traditional text classification methods often struggle with the intricacies of category labels, hierarchical relationships, and the scarcity of annotated data samples. This study presents an advanced medical text classification method utilizing the ALBERT pre-trained language model for health queries. We introduce the TLCM and TCLA models, which apply transfer learning and ensemble learning to enhance classification accuracy. By fine-tuning the ALBERT model and integrating CNN, Bi-LSTM, and Attention mechanisms, our models achieve approximately 91% in Precision, Recall, and Micro_F1, significantly improving upon traditional classification methods. This approach demonstrates the potential of pre-trained language models in medical text mining.

References
Cover Image
Downloads
Published
2024-09-30
Section
Articles
License
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Academic Scholar Hub Press also operates under the Creative Commons Licence CC-BY 4.0. This allows for copy and redistribute the material in any medium or format for any purpose, even commercially. The premise is that you must provide appropriate citation information.

How to Cite

Cang, Y., Yang, W., Sun, D., Ye, Z., & Zheng, Z. (2024). ALBERT-Driven Ensemble Learning for Medical Text Classification. Journal of Computer Technology and Software, 3(6). https://doi.org/10.5281/zenodo.13910447

Most read articles by the same author(s)