论文标题
救援隐式和长尾案件：最近的邻居关系提取
Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction
论文作者
论文摘要
关系提取（RE）在培训预训练的语言模型的帮助下取得了显着的进步。但是，现有的RE模型通常无法处理两种情况：由语言复杂性和数据稀疏引起的隐性表达式和长尾关系类型。在本文中，我们介绍了使用$ k $最近的邻居（$ k $ nn-re）的简单增强。 $ k $ nn-re允许该模型通过最近的邻居搜索在测试时间咨询培训关系，并提供了一种简单而有效的方法来解决上述两个问题。此外，我们观察到，$ k $ nn-re是利用遥远监督（DS）数据的有效方法。实验结果表明，提议的$ k $ nn-re可以在各种监督的RE数据集（即ACE05，SCIERC和WIKI80）上实现最先进的性能，同时在允许使用ds的设置中，在I2B2和WIKI80数据集中效仿I2B2和WIKI80数据集的最佳模型。我们的代码和型号可在以下网址提供：https：//github.com/yukinowan/knn-re。
Relation extraction (RE) has achieved remarkable progress with the help of pre-trained language models. However, existing RE models are usually incapable of handling two situations: implicit expressions and long-tail relation types, caused by language complexity and data sparsity. In this paper, we introduce a simple enhancement of RE using $k$ nearest neighbors ($k$NN-RE). $k$NN-RE allows the model to consult training relations at test time through a nearest-neighbor search and provides a simple yet effective means to tackle the two issues above. Additionally, we observe that $k$NN-RE serves as an effective way to leverage distant supervision (DS) data for RE. Experimental results show that the proposed $k$NN-RE achieves state-of-the-art performances on a variety of supervised RE datasets, i.e., ACE05, SciERC, and Wiki80, along with outperforming the best model to date on the i2b2 and Wiki80 datasets in the setting of allowing using DS. Our code and models are available at: https://github.com/YukinoWan/kNN-RE.
