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

Introduction

The code provided at this page was used to do the experiments presented in [1] (pdf).

It is written in Theano [2], the CRF layer is based on [3].

Resources

Github

Code and configs: globalNormalization_noData.zip

Code and configs including preprocessed dataset and pretrained models: globalNormalization_all.zip

Cite

If you use the provided code in your work, please cite the following paper:

@inproceedings{globalAdel2017,
  author = {Heike Adel and Hinrich Sch\"{u}tze},
  title = {Global Normalization of Convolutional Neural Networks for
Joint Entity and Relation Classification},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics}
}

References

[1] Heike Adel and Hinrich Schütze: "Global Normalization of Convolutional Neural Networks for Joint Entity and Relation Classification", EMNLP 2017. pdf

[2] Theano Development Team: "Theano: A Python framework for fast computation of mathematical expressions", arXiv preprint arXiv:1605.02688, 2016.

[3] Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami and Chris Dyer: "Neural Architectures for Named Entity Recognition", NAACL 2016. github

Contact: Heike Adel (website)