FLEX: Faithful Linguistic Explanations for Neural Net Based Model Decisions


  • Sandareka Wickramanayake National University of Singapore
  • Wynne Hsu National University of Singapore
  • Mong Li Lee National University of Singapore




Explaining the decisions of a Deep Learning Network is imperative to safeguard end-user trust. Such explanations must be intuitive, descriptive, and faithfully explain why a model makes its decisions. In this work, we propose a framework called FLEX (Faithful Linguistic EXplanations) that generates post-hoc linguistic justifications to rationalize the decision of a Convolutional Neural Network. FLEX explains a model’s decision in terms of features that are responsible for the decision. We derive a novel way to associate such features to words, and introduce a new decision-relevance metric that measures the faithfulness of an explanation to a model’s reasoning. Experiment results on two benchmark datasets demonstrate that the proposed framework can generate discriminative and faithful explanations compared to state-of-the-art explanation generators. We also show how FLEX can generate explanations for images of unseen classes as well as automatically annotate objects in images.




How to Cite

Wickramanayake, S., Hsu, W., & Lee, M. L. (2019). FLEX: Faithful Linguistic Explanations for Neural Net Based Model Decisions. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 2539-2546. https://doi.org/10.1609/aaai.v33i01.33012539



AAAI Technical Track: Human-AI Collaboration