A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition
This work is significant for researchers and practitioners in natural language processing who need to build NER systems in low-resource settings without access to expensive domain-specific knowledge.
This paper addresses the challenge of low-resource Named Entity Recognition (NER) without relying on expensive domain-specific resources. The proposed RDANER approach achieves the best performance using only cheap resources and competitive results against state-of-the-art methods that utilize difficult-to-obtain domain-specific resources.
Recently, it has attracted much attention to build reliable named entity recognition (NER) systems using limited annotated data. Nearly all existing works heavily rely on domain-specific resources, such as external lexicons and knowledge bases. However, such domain-specific resources are often not available, meanwhile it's difficult and expensive to construct the resources, which has become a key obstacle to wider adoption. To tackle the problem, in this work, we propose a novel robust and domain-adaptive approach RDANER for low-resource NER, which only uses cheap and easily obtainable resources. Extensive experiments on three benchmark datasets demonstrate that our approach achieves the best performance when only using cheap and easily obtainable resources, and delivers competitive results against state-of-the-art methods which use difficultly obtainable domainspecific resources. All our code and corpora can be found on https://github.com/houking-can/RDANER.