Inspired by recent advances in retrieval augmented methods in
NLP~\citep{khandelwal2019generalization,khandelwal2020nearest,meng2021gnn}, in
this paper, we introduce a $k$ nearest neighbor NER ($k$NN-NER) framework,
which augments the distribution of entity labels by assigning $k$ nearest
neighbors retrieved from the training set. This strategy makes the model more
capable of handling long-tail cases, along with better few-shot learning
abilities. $k$NN-NER requires no additional operation during the training
phase, and by interpolating $k$ nearest neighbors search into the vanilla NER
model, $k$NN-NER consistently outperforms its vanilla counterparts: we achieve
a new state-of-the-art F1-score of 72.03 (+1.25) on the Chinese Weibo dataset
and improved results on a variety of widely used NER benchmarks. Additionally,
we show that $k$NN-NER can achieve comparable results to the vanilla NER model
with 40\% less amount of training data. Code available at
https://github.com/ShannonAI/KNN-NER.

本文介绍了一种新的基于 $k$NN 的实体标注框架，运用 $k$ nearest neighbor 方法来增强实体标签的分布，提高 NER 的 few-shot 学习能力和对 long-tail cases 的处理能力，并在多个数据集上验证和比较其性能，达到了比目前最好的结果更好的 F1 分数。