Filtered BERT: Similarity Filter-Based Augmentation with Bidirectional Transfer Learning for Protected Health Information Prediction in Clinical Documents
- Authors
- Kang, Min; Lee, Kye Hwa; Lee, Youngho
- Issue Date
- Apr-2021
- Publisher
- MDPI
- Keywords
- Augmentation; Named-entity recognition; Protected health information; Transfer learning
- Citation
- APPLIED SCIENCES-BASEL, v.11, no.8
- Journal Title
- APPLIED SCIENCES-BASEL
- Volume
- 11
- Number
- 8
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/81052
- DOI
- 10.3390/app11083668
- ISSN
- 2076-3417
- Abstract
- For the secondary use of clinical documents, it is necessary to de-identify protected health information (PHI) in documents. However, the difficulty lies in the fact that there are few publicly annotated PHI documents. To solve this problem, in this study, we propose a filtered bidirectional encoder representation from transformers (BERT)-based method that predicts a masked word and validates the word again through a similarity filter to construct augmented sentences. The proposed method effectively performs data augmentation. The results show that the augmentation method based on filtered BERT improved the performance of the model. This suggests that our method can effectively improve the performance of the model in the limited data environment. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - IT융합대학 > 컴퓨터공학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/81052)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.