Interpretability

PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks NeurIPS 2020 Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview ACL 2020 Probing Natural Language Inference Models through Semantic Fragments AAAI 2020 Probing Pretrained Language Models for Lexical Semantics EMNLP 2020 Rationalizing Medical Relation Prediction from Corpus-level Statistics ACL 2020 Regularizing Black-box Models for Improved Interpretability NeurIPS 2020 Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks AAAI 2020 SAM: The Sensitivity of Attribution Methods to Hyperparameters CVPR 2020 Sanity Checks for Saliency Metrics AAAI 2020 SCOUT: Self-Aware Discriminant Counterfactual Explanations CVPR 2020 Structured Self-Attention Weights Encode Semantics in Sentiment Analysis EMNLP 2020 Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness? ACL 2020 Towards Interpretable Natural Language Understanding with Explanations as Latent Variables NeurIPS 2020 Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract) AAAI 2020 Transparent Classification with Multilayer Logical Perceptrons and Random Binarization AAAI 2020 Understanding Attention for Text Classification ACL 2020 Understanding Neural Abstractive Summarization Models via Uncertainty EMNLP 2020 Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains EMNLP 2020 Word-Level Contextual Sentiment Analysis with Interpretability AAAI 2020 Zero-Shot Rationalization by Multi-Task Transfer Learning from Question Answering EMNLP 2020 Abduction-Based Explanations for Machine Learning Models AAAI 2019 A Benchmark for Interpretability Methods in Deep Neural Networks NeurIPS 2019 Accurate Layerwise Interpretable Competence Estimation NeurIPS 2019 Addressing Failure Prediction by Learning Model Confidence NeurIPS 2019 AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models EMNLP 2019