Evaluating neural network explanation methods using hybrid documents and morphological agreement

19 January 2018

Papers citing "Evaluating neural network explanation methods using hybrid documents and morphological agreement"

2 / 2 papers shown

Title
Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness? Alon Jacovi Yoav Goldberg XAI 43 571 0 07 Apr 2020
Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods Oana-Maria Camburu Eleonora Giunchiglia Jakob N. Foerster Thomas Lukasiewicz Phil Blunsom FAtt AAML 31 60 0 04 Oct 2019