Named Entity Recognition using context similarity data augmentation

This paper is an extended abstract of a recent work, in which we introduce COSINER, a novel approach to enhancing Named Entity Recognition (NER) tasks through data augmentation. Unlike traditional methods that risk introducing noise, COSINER leverages context similarity to substitute entity mentions with more contextually appropriate ones, yielding superior performance in limited-data scenarios. Experimental results demonstrate COSINER’s effectiveness over existing baselines, with computational times comparable to basic augmentation methods and superior to pre-trained model-based approaches.