Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition

TL;DR

This paper introduces MUCO, a novel approach for few-shot NER that automatically induces undefined classes from other-class words, improving classification accuracy and semantic understanding in low-data scenarios.

Contribution

The paper proposes MUCO, a new model that enhances few-shot NER by leveraging undefined classes from other-class words, addressing overfitting and semantic differentiation issues.

Findings

Outperforms five state-of-the-art models in 1-shot and 5-shot settings

Improves discriminative ability of NER classifiers

Enhances understanding of predefined classes with extra semantic knowledge

Abstract

Few-shot Named Entity Recognition (NER) exploits only a handful of annotations to identify and classify named entity mentions. Prototypical network shows superior performance on few-shot NER. However, existing prototypical methods fail to differentiate rich semantics in other-class words, which will aggravate overfitting under few shot scenario. To address the issue, we propose a novel model, Mining Undefined Classes from Other-class (MUCO), that can automatically induce different undefined classes from the other class to improve few-shot NER. With these extra-labeled undefined classes, our method will improve the discriminative ability of NER classifier and enhance the understanding of predefined classes with stand-by semantic knowledge. Experimental results demonstrate that our model outperforms five state-of-the-art models in both 1-shot and 5-shots settings on four NER benchmarks. We will release the code upon acceptance. The source code is released on https: //github.com/shuaiwa16/OtherClassNER.git.