model interpretability

Adaptive Transformers for Learning Multimodal Representations ACL 2020 A Diagnostic Study of Explainability Techniques for Text Classification EMNLP 2020 AI Explainability 360: An Extensible Toolkit for Understanding Data and Machine Learning Models JMLR 2020 AI Trust in Business Processes: The Need for Process-Aware Explanations AAAI 2020 An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction EMNLP 2020 A Survey of the State of Explainable AI for Natural Language Processing AACL 2020 Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability NeurIPS 2020 BERT-Based Neural Collaborative Filtering and Fixed-Length Contiguous Tokens Explanation AACL 2020 Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses NeurIPS 2020 Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models NeurIPS 2020 Certifai: A Toolkit for Building Trust in AI Systems IJCAI 2020 Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling ACL 2020 Debugging Tests for Model Explanations NeurIPS 2020 DeepCoDA: personalized interpretability for compositional health data ICML 2020 DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction IJCAI 2020 Dynamic Network Pruning with Interpretable Layerwise Channel Selection AAAI 2020 Efficient Estimation of Influence of a Training Instance EMNLP 2020 ERASER: A Benchmark to Evaluate Rationalized NLP Models ACL 2020 Evaluating and Aggregating Feature-based Model Explanations IJCAI 2020 Explanation by Progressive Exaggeration ICLR 2020 Exploring Weaknesses of VQA Models through Attribution Driven Insights ACL 2020 Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection ACL 2020 Gradient-based Analysis of NLP Models is Manipulable EMNLP 2020 Inserting Information Bottlenecks for Attribution in Transformers EMNLP 2020 Interpretable Companions for Black-Box Models AISTATS 2020