In-Context Learning for Few-Shot Nested Named Entity Recognition
This work addresses the data annotation bottleneck for nested NER, which is important for NLP practitioners working with limited labeled data.
The authors tackled the problem of few-shot nested named entity recognition by introducing an in-context learning framework with a novel demonstration selection mechanism called EnDe retriever, achieving state-of-the-art performance across three nested and four flat NER datasets.
In nested Named entity recognition (NER), entities are nested with each other, and thus requiring more data annotations to address. This leads to the development of few-shot nested NER, where the prevalence of pretrained language models with in-context learning (ICL) offers promising solutions. In this work, we introduce an effective and innovative ICL framework for the setting of few-shot nested NER. We improve the ICL prompt by devising a novel example demonstration selection mechanism, EnDe retriever. In EnDe retriever, we employ contrastive learning to perform three types of representation learning, in terms of semantic similarity, boundary similarity, and label similarity, to generate high-quality demonstration examples. Extensive experiments over three nested NER and four flat NER datasets demonstrate the efficacy of our system.