/Explainable-NER

Primary LanguageJupyter Notebook

Explainable-NER

Applying Layer-wise Relevance Propagation (LRP) to make Named Entity Recognition (NER) explainable. The NER model is implemented with Bi-directional LSTM (Bi-LSTM) and Conditional Random Field (CRF).

Environment:

  • Python 3.5
  • Keras 2.1.5
  • Sickit-learn 0.19.1
  • Pandas 0.22.0
  • Numpy 1.14.2
  • Matplotlib 2.2.2

Acknowledgments

Explaining Recurrent Neural Network Predictions in Sentiment Analysis by Arras, Leila, et al, 2017

Explaining Recurrent Neural Network Predictions in Sentiment Analysis, code

Explaining Recurrent Neural Network Predictions in Sentiment Analysis by L. Arras, G. Montavon, K.-R. Müller and W. Samek, 2017

Visualizing and Understanding Neural Models in NLP by J. Li, X. Chen, E. Hovy and D. Jurafsky, 2016

Visualizing and understanding neural machine translation by Ding, Yanzhuo, et al. 2017