model interpretability

Interpretation of NLP models through input marginalization EMNLP 2020 Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge ICML 2020 Investigating Gender Bias in Language Models Using Causal Mediation Analysis NeurIPS 2020 Learning Deep Attribution Priors Based On Prior Knowledge NeurIPS 2020 Learning to Deceive with Attention-Based Explanations ACL 2020 Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers EMNLP 2020 LS-Tree: Model Interpretation When the Data Are Linguistic AAAI 2020 Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations ACL 2020 Model Interpretability through the lens of Computational Complexity NeurIPS 2020 NILE : Natural Language Inference with Faithful Natural Language Explanations ACL 2020 Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection ACL 2020 On Counterfactual Explanations under Predictive Multiplicity UAI 2020 Parameterized Explainer for Graph Neural Network NeurIPS 2020 Pareto Probing: Trading Off Accuracy for Complexity EMNLP 2020 Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT ACL 2020 Quantifying Attention Flow in Transformers ACL 2020 Sanity Checks for Saliency Metrics AAAI 2020 SQuINTing at VQA Models: Introspecting VQA Models With Sub-Questions CVPR 2020 The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? EMNLP 2020 The Explanation Game: Towards Prediction Explainability through Sparse Communication EMNLP 2020 The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models EMNLP 2020 Towards Global Explanations of Convolutional Neural Networks With Concept Attribution CVPR 2020 Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models ICLR 2020 Towards Visually Explaining Variational Autoencoders CVPR 2020 Transparency Promotion with Model-Agnostic Linear Competitors ICML 2020