Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework
This addresses the problem of limited labeled data for NER, enabling identification of unseen entity classes, though it is incremental as it builds on pre-trained language models.
The paper tackles low-resource named entity recognition (NER) in few-shot and zero-shot settings by proposing SpanNER, a framework that learns from natural language supervision without in-domain labeled data, achieving average improvements of 10%, 23%, and 26% over baselines in few-shot learning, domain transfer, and zero-shot learning respectively.
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.