Decomposed Meta-Learning for Few-Shot Named Entity Recognition
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.
Cite
@article{arxiv.2204.05751,
title = {Decomposed Meta-Learning for Few-Shot Named Entity Recognition},
author = {Tingting Ma and Huiqiang Jiang and Qianhui Wu and Tiejun Zhao and Chin-Yew Lin},
journal= {arXiv preprint arXiv:2204.05751},
year = {2022}
}
Comments
This paper has been accepted for publication in Findings of ACL 2022. Code is available at: https://github.com/microsoft/vert-papers/tree/master/papers/DecomposedMetaNER