Example-Based Named Entity Recognition

08/24/2020

∙

by   Morteza Ziyadi, et al.

∙

0

∙

share

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.