Self-Training using Rules of Grammar for Few-Shot NLU

Joonghyuk Hahn, Hyunjoon Cheon, Kyuyeol Han, Cheongjae Lee, Junseok Kim, Yo-Sub Han


Abstract
We tackle the problem of self-training networks for NLU in low-resource environment—few labeled data and lots of unlabeled data. The effectiveness of self-training is a result of increasing the amount of training data while training. Yet it becomes less effective in low-resource settings due to unreliable labels predicted by the teacher model on unlabeled data. Rules of grammar, which describe the grammatical structure of data, have been used in NLU for better explainability. We propose to use rules of grammar in self-training as a more reliable pseudo-labeling mechanism, especially when there are few labeled data. We design an effective algorithm that constructs and expands rules of grammar without human involvement. Then we integrate the constructed rules as a pseudo-labeling mechanism into self-training. There are two possible scenarios regarding data distribution: it is unknown or known in prior to training. We empirically demonstrate that our approach substantially outperforms the state-of-the-art methods in three benchmark datasets for both scenarios.
Anthology ID:
2021.findings-emnlp.389
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4576–4581
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.389
DOI:
10.18653/v1/2021.findings-emnlp.389
Bibkey:
Cite (ACL):
Joonghyuk Hahn, Hyunjoon Cheon, Kyuyeol Han, Cheongjae Lee, Junseok Kim, and Yo-Sub Han. 2021. Self-Training using Rules of Grammar for Few-Shot NLU. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4576–4581, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Self-Training using Rules of Grammar for Few-Shot NLU (Hahn et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.389.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.389.mp4