Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding

Jianing Wang, Qiushi Sun, Nuo Chen, Chengyu Wang, Jun Huang, Ming Gao, Xiang Li


Abstract
The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the predominant semi-supervised learning (SSL) approaches, which utilizes large-scale unlabeled data to generate synthetic examples. However, too many noisy labels will hurt the model performance, and the self-training procedure requires multiple training iterations making it more expensive if all the model parameters of the PLM are updated. This paper presents UPET, a novel Uncertainty-aware Parameter-Efficient self-Training framework to effectively and efficiently address the labeled data scarcity issue. Specifically, we incorporate Monte Carlo (MC) dropout in Bayesian neural network (BNN) to perform uncertainty estimation for the teacher model and then judiciously select reliable pseudo-labeled examples based on confidence and certainty. During the student training, we introduce multiple parameter-efficient learning (PEL) paradigms that allow optimizes only a small percentage of parameters. We also propose a novel Easy-Hard Contrastive Tuning to enhance the robustness and generalization. Extensive experiments over multiple downstream tasks demonstrate that UPET achieves a substantial improvement in terms of performance and efficiency. Our codes and data are released at https: //github.com/wjn1996/UPET.
Anthology ID:
2023.findings-emnlp.528
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7873–7884
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.528
DOI:
10.18653/v1/2023.findings-emnlp.528
Bibkey:
Cite (ACL):
Jianing Wang, Qiushi Sun, Nuo Chen, Chengyu Wang, Jun Huang, Ming Gao, and Xiang Li. 2023. Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7873–7884, Singapore. Association for Computational Linguistics.
Cite (Informal):
Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding (Wang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.528.pdf