Global Normalization of Convolutional Neural Networks for Joint Entity and Relation Classification
This work addresses the problem of improving accuracy in information extraction tasks for natural language processing researchers, though it appears incremental as it builds on existing methods with a specific architectural change.
The paper tackled joint entity classification and relation extraction by introducing globally normalized convolutional neural networks with a linear-chain conditional random field output layer, achieving performance improvements over a locally normalized softmax layer on a benchmark dataset.
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.