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

Heike Adel, Hinrich Schütze


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.
Anthology ID:
D17-1181
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1723–1729
Language:
URL:
https://aclanthology.org/D17-1181
DOI:
10.18653/v1/D17-1181
Bibkey:
Cite (ACL):
Heike Adel and Hinrich Schütze. 2017. Global Normalization of Convolutional Neural Networks for Joint Entity and Relation Classification. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1723–1729, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Global Normalization of Convolutional Neural Networks for Joint Entity and Relation Classification (Adel & Schütze, EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1181.pdf