Interpretability

Analytical Methods for Interpretable Ultradense Word Embeddings EMNLP 2019 Approximate Feature Collisions in Neural Nets NeurIPS 2019 Attention is not not Explanation EMNLP 2019 Axiomatic Characterization of Data-Driven Influence Measures for Classification AAAI 2019 Correlating Neural and Symbolic Representations of Language ACL 2019 CXPlain: Causal Explanations for Model Interpretation under Uncertainty NeurIPS 2019 Demystifying Black-box Models with Symbolic Metamodels NeurIPS 2019 Desiderata for Interpretability: Explaining Decision Tree Predictions with Counterfactuals AAAI 2019 Evaluating Recurrent Neural Network Explanations ACL 2019 Explainability Methods for Graph Convolutional Neural Networks CVPR 2019 Explicit Bias Discovery in Visual Question Answering Models CVPR 2019 Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression CVPR 2019 FLEX: Faithful Linguistic Explanations for Neural Net Based Model Decisions AAAI 2019 Granger-Causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks AAAI 2019 Grid Saliency for Context Explanations of Semantic Segmentation NeurIPS 2019 Guiding the Flowing of Semantics: Interpretable Video Captioning via POS Tag EMNLP 2019 Human-grounded Evaluations of Explanation Methods for Text Classification EMNLP 2019 Incorporating Priors with Feature Attribution on Text Classification ACL 2019 Interpreting Deep Models for Text Analysis via Optimization and Regularization Methods AAAI 2019 Learning Interpretable Negation Rules via Weak Supervision at Document Level: A Reinforcement Learning Approach NAACL 2019 L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data ICLR 2019 Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification EMNLP 2019 Modeling Paths for Explainable Knowledge Base Completion ACL 2019 NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks AAAI 2019 On the Accuracy of Influence Functions for Measuring Group Effects NeurIPS 2019