A Unified Label-Aware Contrastive Learning Framework for Few-Shot Named Entity Recognition

TL;DR

This paper introduces a label-aware contrastive learning framework for few-shot NER that enhances contextual representations by integrating label semantics and optimizing multiple contrastive objectives, leading to significant performance gains.

Contribution

It proposes a unified token-level contrastive learning approach that incorporates label semantics as prompts and optimizes multiple contrastive objectives for improved few-shot NER.

Findings

Outperforms state-of-the-art models by 7% in micro F1 scores.

Effective across diverse test domains and large-scale datasets.

Enhances transferability and contextual discriminability of NER models.

Abstract

Few-shot Named Entity Recognition (NER) aims to extract named entities using only a limited number of labeled examples. Existing contrastive learning methods often suffer from insufficient distinguishability in context vector representation because they either solely rely on label semantics or completely disregard them. To tackle this issue, we propose a unified label-aware token-level contrastive learning framework. Our approach enriches the context by utilizing label semantics as suffix prompts. Additionally, it simultaneously optimizes context-context and context-label contrastive learning objectives to enhance generalized discriminative contextual representations.Extensive experiments on various traditional test domains (OntoNotes, CoNLL'03, WNUT'17, GUM, I2B2) and the large-scale few-shot NER dataset (FEWNERD) demonstrate the effectiveness of our approach. It outperforms prior state-of-the-art models by a significant margin, achieving an average absolute gain of 7% in micro F1 scores across most scenarios. Further analysis reveals that our model benefits from its powerful transfer capability and improved contextual representations.