Abstract
Few-shot named entity recognition (NER) targets generalizing to unseen labels and/or domains with few labeled examples. Existing metric learning methods compute token-level similarities between query and support sets, but are not able to fully incorporate label semantics into modeling. To address this issue, we propose a simple method to largely improve metric learning for NER: 1) multiple prompt schemas are designed to enhance label semantics; 2) we propose a novel architecture to effectively combine multiple prompt-based representations.Empirically, our method achieves new state-of-the-art (SOTA) results under 16 of the 18 considered settings, substantially outperforming the previous SOTA by an average of 9.12% and a maximum of 34.51% in relative gains of micro F1.- Anthology ID:
- 2023.findings-acl.451
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7199–7212
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.451
- DOI:
- 10.18653/v1/2023.findings-acl.451
- Cite (ACL):
- Yanru Chen, Yanan Zheng, and Zhilin Yang. 2023. Prompt-Based Metric Learning for Few-Shot NER. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7199–7212, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Prompt-Based Metric Learning for Few-Shot NER (Chen et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2023.findings-acl.451.pdf