Global Normalization of Convolutional Neural Networks for Joint Entity and Relation Classification

07/24/2017

∙

by   Heike Adel, et al.

∙

0

∙

share

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.