In-Context Learning for Few-Shot Nested Named Entity Recognition

TL;DR

This paper presents a novel in-context learning framework for few-shot nested NER, utilizing a new example selection method called EnDe retriever that improves demonstration quality through contrastive learning.

Contribution

The work introduces EnDe retriever, a contrastive learning-based demonstration selection mechanism, enhancing in-context learning for few-shot nested NER.

Findings

Significant performance improvements on nested NER datasets

Effective demonstration selection via contrastive learning

Robustness across multiple datasets and NER types

Abstract

In nested Named entity recognition (NER), entities are nested with each other, and thus requiring more data annotations to address. This leads to the development of few-shot nested NER, where the prevalence of pretrained language models with in-context learning (ICL) offers promising solutions. In this work, we introduce an effective and innovative ICL framework for the setting of few-shot nested NER. We improve the ICL prompt by devising a novel example demonstration selection mechanism, EnDe retriever. In EnDe retriever, we employ contrastive learning to perform three types of representation learning, in terms of semantic similarity, boundary similarity, and label similarity, to generate high-quality demonstration examples. Extensive experiments over three nested NER and four flat NER datasets demonstrate the efficacy of our system.