Abstract
Neural named entity recognition (NER) models may easily encounter the over-confidence issue, which degrades the performance and calibration. Inspired by label smoothing and driven by the ambiguity of boundary annotation in NER engineering, we propose boundary smoothing as a regularization technique for span-based neural NER models. It re-assigns entity probabilities from annotated spans to the surrounding ones. Built on a simple but strong baseline, our model achieves results better than or competitive with previous state-of-the-art systems on eight well-known NER benchmarks. Further empirical analysis suggests that boundary smoothing effectively mitigates over-confidence, improves model calibration, and brings flatter neural minima and more smoothed loss landscapes.- Anthology ID:
- 2022.acl-long.490
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7096–7108
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.490
- DOI:
- 10.18653/v1/2022.acl-long.490
- Cite (ACL):
- Enwei Zhu and Jinpeng Li. 2022. Boundary Smoothing for Named Entity Recognition. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7096–7108, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Boundary Smoothing for Named Entity Recognition (Zhu & Li, ACL 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.acl-long.490.pdf
- Code
- syuoni/eznlp
- Data
- ACE 2004, ACE 2005, CoNLL, CoNLL 2003, CoNLL++, MSRA CN NER, OntoNotes 4.0, OntoNotes 5.0, Resume NER, Weibo NER