Abstract
Named Entity Recognition (NER), as a crucial subtask in natural language processing (NLP), suffers from limited labeled samples (a.k.a. few-shot). Meta-learning methods are widely used for few-shot NER, but these existing methods overlook the importance of label dependency for NER, resulting in suboptimal performance. However, applying meta-learning methods to label dependency learning faces a special challenge, that is, due to the discrepancy of label sets in different domains, the label dependencies can not be transferred across domains. In this paper, we propose the Task-adaptive Label Dependency Transfer (TLDT) method to make label dependency transferable and effectively adapt to new tasks by a few samples. TLDT improves the existing optimization-based meta-learning methods by learning general initialization and individual parameter update rule for label dependency. Extensive experiments show that TLDT achieves significant improvement over the state-of-the-art methods.- Anthology ID:
- 2023.findings-acl.203
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3280–3293
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.203
- DOI:
- 10.18653/v1/2023.findings-acl.203
- Cite (ACL):
- Shan Zhang, Bin Cao, Tianming Zhang, Yuqi Liu, and Jing Fan. 2023. Task-adaptive Label Dependency Transfer for Few-shot Named Entity Recognition. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3280–3293, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Task-adaptive Label Dependency Transfer for Few-shot Named Entity Recognition (Zhang et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/2023.findings-acl.203.pdf