Revisiting Self-training for Few-shot Learning of Language Model
Yiming Chen, Yan Zhang, Chen Zhang, Grandee Lee, Ran Cheng, Haizhou Li
Abstract
As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM. Given two views of a text sample via weak and strong augmentation techniques, SFLM generates a pseudo label on the weakly augmented version. Then, the model predicts the same pseudo label when fine-tuned with the strongly augmented version. This simple approach is shown to outperform other state-of-the-art supervised and semi-supervised counterparts on six sentence classification and six sentence-pair classification benchmarking tasks. In addition, SFLM only relies on a few in-domain unlabeled data. We conduct a comprehensive analysis to demonstrate the robustness of our proposed approach under various settings, including augmentation techniques, model scale, and few-shot knowledge transfer across tasks.- Anthology ID:
- 2021.emnlp-main.718
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9125–9135
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.718
- DOI:
- 10.18653/v1/2021.emnlp-main.718
- Cite (ACL):
- Yiming Chen, Yan Zhang, Chen Zhang, Grandee Lee, Ran Cheng, and Haizhou Li. 2021. Revisiting Self-training for Few-shot Learning of Language Model. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9125–9135, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Revisiting Self-training for Few-shot Learning of Language Model (Chen et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.emnlp-main.718.pdf
- Code
- matthewcym/sflm
- Data
- GLUE, MPQA Opinion Corpus, MRPC, MultiNLI, QNLI, SNLI, SST