论文标题
基于示例的命名实体识别
Example-Based Named Entity Recognition
论文作者
论文摘要
在我们称基于示例的NER的稀缺数据的存在下，我们提出了一种新的方法来指定实体识别（NER）。我们的无火车学习方法从提问中汲取灵感，以识别实体跨越新的且看不见的领域。与当前的最新方法相比，所提出的方法的性能明显更好，尤其是在使用较少数量的支持示例时。
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.
