Interpretability

Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spaces AAAI 2020 Well-Calibrated Regression Uncertainty in Medical Imaging with Deep Learning MIDL 2020 What Can Neural Networks Reason About? ICLR 2020 What Did You Think Would Happen? Explaining Agent Behaviour through Intended Outcomes NeurIPS 2020 What Does an End-to-End Dialect Identification Model Learn About Non-Dialectal Information? Interspeech 2020 What Does BERT with Vision Look At? ACL 2020 What’s so special about BERT’s layers? A closer look at the NLP pipeline in monolingual and multilingual models EMNLP 2020 What went wrong and when? Instance-wise feature importance for time-series black-box models NeurIPS 2020 When Explanations Lie: Why Many Modified BP Attributions Fail ICML 2020 White Noise Analysis of Neural Networks ICLR 2020 Why Did the x-Vector System Miss a Target Speaker? Impact of Acoustic Mismatch Upon Target Score on VoxCeleb Data Interspeech 2020 Why do you think that? Exploring Faithful Sentence-Level Rationales Without Supervision EMNLP 2020 WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge ACL 2020 Word-Level Contextual Sentiment Analysis with Interpretability AAAI 2020 Word-Level Uncertainty Estimation for Black-Box Text Classifiers using RNNs COLING 2020 Would you describe a leopard as yellow? Evaluating crowd-annotations with justified and informative disagreement COLING 2020 X-CAL: Explicit Calibration for Survival Analysis NeurIPS 2020 Your classifier is secretly an energy based model and you should treat it like one ICLR 2020 Zero-Shot Rationalization by Multi-Task Transfer Learning from Question Answering EMNLP 2020 A Bayesian Perspective on the Deep Image Prior CVPR 2019 Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation NAACL 2019 Abduction-Based Explanations for Machine Learning Models AAAI 2019 Accurate and Interpretable Factorization Machines AAAI 2019 Accurate Layerwise Interpretable Competence Estimation NeurIPS 2019 Adaptive Activation Thresholding: Dynamic Routing Type Behavior for Interpretability in Convolutional Neural Networks ICCV 2019