Abstract
Few-shot Text Classification predicts the semantic label of a given text with a handful of supporting instances. Current meta-learning methods have achieved satisfying results in various few-shot situations. Still, they often require a large amount of data to construct many few-shot tasks for meta-training, which is not practical in real-world few-shot scenarios. Prompt-tuning has recently proved to be another effective few-shot learner by bridging the gap between pre-train and downstream tasks. In this work, we closely combine the two promising few-shot learning methodologies in structure and propose a Prompt-Based Meta-Learning (PBML) model to overcome the above meta-learning problem by adding the prompting mechanism. PBML assigns label word learning to base-learners and template learning to meta-learner, respectively. Experimental results show state-of-the-art performance on four text classification datasets under few-shot settings, with higher accuracy and good robustness. We demonstrate through low-resource experiments that our method alleviates the shortcoming that meta-learning requires too much data for meta-training. In the end, we use the visualization to interpret and verify that the meta-learning framework can help the prompting method converge better. We release our code to reproduce our experiments.- Anthology ID:
- 2022.emnlp-main.87
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1342–1357
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.87
- DOI:
- 10.18653/v1/2022.emnlp-main.87
- Cite (ACL):
- Haoxing Zhang, Xiaofeng Zhang, Haibo Huang, and Lei Yu. 2022. Prompt-Based Meta-Learning For Few-shot Text Classification. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1342–1357, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Prompt-Based Meta-Learning For Few-shot Text Classification (Zhang et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2022.emnlp-main.87.pdf