@inproceedings{sushil-etal-2018-rule,
    title = "Rule induction for global explanation of trained models",
    author = "Sushil, Madhumita  and
      {\v{S}}uster, Simon  and
      Daelemans, Walter",
    editor = "Linzen, Tal  and
      Chrupa{\l}a, Grzegorz  and
      Alishahi, Afra",
    booktitle = "Proceedings of the 2018 {EMNLP} Workshop {B}lackbox{NLP}: Analyzing and Interpreting Neural Networks for {NLP}",
    month = nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/W18-5411/",
    doi = "10.18653/v1/W18-5411",
    pages = "82--97",
    abstract = "Understanding the behavior of a trained network and finding explanations for its outputs is important for improving the network{'}s performance and generalization ability, and for ensuring trust in automated systems. Several approaches have previously been proposed to identify and visualize the most important features by analyzing a trained network. However, the relations between different features and classes are lost in most cases. We propose a technique to induce sets of if-then-else rules that capture these relations to globally explain the predictions of a network. We first calculate the importance of the features in the trained network. We then weigh the original inputs with these feature importance scores, simplify the transformed input space, and finally fit a rule induction model to explain the model predictions. We find that the output rule-sets can explain the predictions of a neural network trained for 4-class text classification from the 20 newsgroups dataset to a macro-averaged F-score of 0.80. We make the code available at \url{https://github.com/clips/interpret_with_rules}."
}