Abstract
Prompt-based learning (i.e., prompting) is an emerging paradigm for exploiting knowledge learned by a pretrained language model. In this paper, we propose Automatic Multi-Label Prompting (AMuLaP), a simple yet effective method to automatically select label mappings for few-shot text classification with prompting. Our method exploits one-to-many label mappings and a statistics-based algorithm to select label mappings given a prompt template. Our experiments demonstrate that AMuLaP achieves competitive performance on the GLUE benchmark without human effort or external resources.- Anthology ID:
- 2022.naacl-main.401
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5483–5492
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.401
- DOI:
- 10.18653/v1/2022.naacl-main.401
- Cite (ACL):
- Han Wang, Canwen Xu, and Julian McAuley. 2022. Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5483–5492, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification (Wang et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2022.naacl-main.401.pdf
- Code
- hannight/amulap
- Data
- CoLA, GLUE, MRPC, MultiNLI, QNLI, SST, SST-2