Interpretability

Reasoning-Based Learning of Interpretable ML Models IJCAI 2021 Recursion in Abstract Argumentation is Hard --- On the Complexity of Semantics Based on Weak Admissibility AAAI 2021 Reference-Free Word- and Sentence-Level Translation Evaluation with Token-Matching Metrics EMNLP 2021 Reinforcement Learning Enhanced Explainer for Graph Neural Networks NeurIPS 2021 Relation-aware Bidirectional Path Reasoning for Commonsense Question Answering CoNLL 2021 Relation Classification with Cognitive Attention Supervision NAACL 2021 Relative Importance in Sentence Processing ACL 2021 Relevance-CAM: Your Model Already Knows Where To Look CVPR 2021 Reliable Post hoc Explanations: Modeling Uncertainty in Explainability NeurIPS 2021 Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting ICLR 2021 Replicating and Extending “Because Their Treebanks Leak”: Graph Isomorphism, Covariants, and Parser Performance ACL 2021 Representation learning for improved interpretability and classification accuracy of clinical factors from EEG ICLR 2021 Representations of Meaning in Neural Networks for NLP: a Thesis Proposal NAACL 2021 Representer Point Selection via Local Jacobian Expansion for Post-hoc Classifier Explanation of Deep Neural Networks and Ensemble Models NeurIPS 2021 Representing Partial Programs with Blended Abstract Semantics ICLR 2021 Responsible Prediction Making of COVID-19 Mortality (Student Abstract) AAAI 2021 Rethinking Calibration of Deep Neural Networks: Do Not Be Afraid of Overconfidence NeurIPS 2021 Rethinking the Role of Gradient-based Attribution Methods for Model Interpretability ICLR 2021 ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering ACL 2021 Re-understanding Finite-State Representations of Recurrent Policy Networks ICML 2021 Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems NeurIPS 2021 Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions AAAI 2021 Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting With Their Explanations CVPR 2021 Robust Counterfactual Explanations on Graph Neural Networks NeurIPS 2021 Robustness between the worst and average case NeurIPS 2021