THUNDER: Named Entity Recognition Using a Teacher-Student Model with Dual Classifiers for Strong and Weak Supervisions
- Authors
- Oh, Seongwoong; Jung, Woohwan; Shim, Kyuseok
- Issue Date
- Oct-2023
- Publisher
- IOS Press
- Citation
- Frontiers in Artificial Intelligence and Applications, v.372, pp 1795 - 1802
- Pages
- 8
- Indexed
- SCOPUS
FOREIGN
- Journal Title
- Frontiers in Artificial Intelligence and Applications
- Volume
- 372
- Start Page
- 1795
- End Page
- 1802
- URI
- https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/115509
- DOI
- 10.3233/FAIA230466
- ISSN
- 0922-6389
1535-6698
- Abstract
- Strong and weak supervisions have complementary characteristics. However, utilizing both supervisions for named entity recognition (NER) has not been extensively studied. Moreover, the existing works address only incomplete annotations and neglects inaccurate annotations during NER model training. To effectively utilize weak labels, we introduce an auxiliary classifier that learns from weak labels. Furthermore, we adopt the teacher-student framework to handle both incomplete and inaccurate weak labels. A teacher model is first trained using both strongly and weakly supervised data, and next generates pseudo labels to replace weak labels. Then, the student model is trained so that the main classifier learns from both strong labels and confident pseudo labels while the auxiliary classifier learns from less confident pseudo labels. We also incorporate data augmentation through ChatGPT to generate additional annotated sentences to improve model performance and generalization capabilities. The experimental results with different weak supervisions demonstrate that our proposed method surpasses existing techniques. © 2023 The Authors.
- Files in This Item
-
Go to Link
- Appears in
Collections - COLLEGE OF COMPUTING > DEPARTMENT OF ARTIFICIAL INTELLIGENCE > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/115509)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.