Decomposed Meta-Learning for Few-Shot Named Entity Recognition

Tingting Ma, Huiqiang Jiang, Qianhui Wu, Tiejun Zhao, Chin-Yew Lin


Abstract
Few-shot named entity recognition (NER) systems aim at recognizing novel-class named entities based on only a few labeled examples. In this paper, we present a decomposed meta-learning approach which addresses the problem of few-shot NER by sequentially tackling few-shot span detection and few-shot entity typing using meta-learning. In particular, we take the few-shot span detection as a sequence labeling problem and train the span detector by introducing the model-agnostic meta-learning (MAML) algorithm to find a good model parameter initialization that could fast adapt to new entity classes. For few-shot entity typing, we propose MAML-ProtoNet, i.e., MAML-enhanced prototypical networks to find a good embedding space that can better distinguish text span representations from different entity classes. Extensive experiments on various benchmarks show that our approach achieves superior performance over prior methods.
Anthology ID:
2022.findings-acl.124
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venues:
ACL | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1584–1596
Language:
URL:
https://aclanthology.org/2022.findings-acl.124
DOI:
10.18653/v1/2022.findings-acl.124
Bibkey:
Cite (ACL):
Tingting Ma, Huiqiang Jiang, Qianhui Wu, Tiejun Zhao, and Chin-Yew Lin. 2022. Decomposed Meta-Learning for Few-Shot Named Entity Recognition. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1584–1596, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Decomposed Meta-Learning for Few-Shot Named Entity Recognition (Ma et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.124.pdf
Software:
 2022.findings-acl.124.software.zip
Code
 microsoft/vert-papers
Data
CoNLL 2002Few-NERDWNUT 2017