Abstract
Few-shot NER needs to effectively capture information from limited instances and transfer useful knowledge from external resources. In this paper, we propose a self-describing mechanism for few-shot NER, which can effectively leverage illustrative instances and precisely transfer knowledge from external resources by describing both entity types and mentions using a universal concept set. Specifically, we design Self-describing Networks (SDNet), a Seq2Seq generation model which can universally describe mentions using concepts, automatically map novel entity types to concepts, and adaptively recognize entities on-demand. We pre-train SDNet with large-scale corpus, and conduct experiments on 8 benchmarks from different domains. Experiments show that SDNet achieves competitive performances on all benchmarks and achieves the new state-of-the-art on 6 benchmarks, which demonstrates its effectiveness and robustness.- Anthology ID:
- 2022.acl-long.392
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5711–5722
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.392
- DOI:
- 10.18653/v1/2022.acl-long.392
- Cite (ACL):
- Jiawei Chen, Qing Liu, Hongyu Lin, Xianpei Han, and Le Sun. 2022. Few-shot Named Entity Recognition with Self-describing Networks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5711–5722, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Few-shot Named Entity Recognition with Self-describing Networks (Chen et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.acl-long.392.pdf
- Code
- chen700564/sdnet
- Data
- WNUT 2017