Example-Based Named Entity Recognition
This addresses the problem of NER in data-scarce scenarios for NLP practitioners, offering a novel method that is not incremental.
The paper tackles named entity recognition (NER) with scarce data by proposing a train-free few-shot learning approach inspired by question-answering, which significantly outperforms the state-of-the-art, especially with low numbers of support examples.
We present a novel approach to named entity recognition (NER) in the presence of scarce data that we call example-based NER. Our train-free few-shot learning approach takes inspiration from question-answering to identify entity spans in a new and unseen domain. In comparison with the current state-of-the-art, the proposed method performs significantly better, especially when using a low number of support examples.