Interpretability

Correlating Neural and Symbolic Representations of Language ACL 2019 Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models ICML 2019 Counterfactuals in Explainable Artificial Intelligence (XAI): Evidence from Human Reasoning IJCAI 2019 Counterfactual Visual Explanations ICML 2019 Deep Gamblers: Learning to Abstain with Portfolio Theory NeurIPS 2019 DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks IJCAI 2019 Deep Neural Model Inspection and Comparison via Functional Neuron Pathways ACL 2019 Deep Neural Networks Constrained by Decision Rules AAAI 2019 Deliberative Explanations: visualizing network insecurities NeurIPS 2019 Demystifying Black-box Models with Symbolic Metamodels NeurIPS 2019 DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare ICCV 2019 Desiderata for Interpretability: Explaining Decision Tree Predictions with Counterfactuals AAAI 2019 Designing and Interpreting Probes with Control Tasks EMNLP 2019 Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features NAACL 2019 Detecting Egregious Responses in Neural Sequence-to-sequence Models ICLR 2019 Discovering Fair Representations in the Data Domain CVPR 2019 Disentangled behavioural representations NeurIPS 2019 Disentangled Relational Representations for Explaining and Learning from Demonstration CoRL 2019 Disentangling Influence: Using disentangled representations to audit model predictions NeurIPS 2019 Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation ACL 2019 Do Human Rationales Improve Machine Explanations? ACL 2019 DoPAMINE: Double-Sided Masked CNN for Pixel Adaptive Multiplicative Noise Despeckling AAAI 2019 Dynamic Explainable Recommendation Based on Neural Attentive Models AAAI 2019 Dynamic Graph Attention for Referring Expression Comprehension ICCV 2019 EASSE: Easier Automatic Sentence Simplification Evaluation EMNLP 2019