Abstract
We introduce globally normalized convolutional neural networks for joint entity classification and relation extraction. In particular, we propose a way to utilize a linear-chain conditional random field output layer for predicting entity types and relations between entities at the same time. Our experiments show that global normalization outperforms a locally normalized softmax layer on a benchmark dataset.
Abstract (translated)
我们引入全局归一化卷积神经网络用于联合实体分类和关系提取。特别地，我们提出了一种利用线性链条件随机场输出层同时预测实体类型和实体之间关系的方法。我们的实验表明，全局归一化优于基准数据集上的局部归一化softmax层。
URL
https://arxiv.org/abs/1707.07719
