Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework

TL;DR

This paper introduces SpanNER, a novel low-resource NER framework that leverages language models and natural language supervision to recognize unseen entity classes in few-shot and zero-shot scenarios, achieving significant improvements.

Contribution

The paper presents a new decomposed framework, SpanNER, for low-resource NER that effectively learns from language descriptions and outperforms existing methods in various low-resource settings.

Findings

Achieves 10% improvement in few-shot NER

Achieves 23% improvement in domain transfer NER

Achieves 26% improvement in zero-shot NER

Abstract

In this work, we study the problem of named entity recognition (NER) in a low resource scenario, focusing on few-shot and zero-shot settings. Built upon large-scale pre-trained language models, we propose a novel NER framework, namely SpanNER, which learns from natural language supervision and enables the identification of never-seen entity classes without using in-domain labeled data. We perform extensive experiments on 5 benchmark datasets and evaluate the proposed method in the few-shot learning, domain transfer and zero-shot learning settings. The experimental results show that the proposed method can bring 10%, 23% and 26% improvements in average over the best baselines in few-shot learning, domain transfer and zero-shot learning settings respectively.