Interpretability

Attention Can Reflect Syntactic Structure (If You Let It) EACL 2021 Attention Flows are Shapley Value Explanations ACL 2021 Attention vs non-attention for a Shapley-based explanation method NAACL 2021 Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions EMNLP 2021 Auditing Black-Box Prediction Models for Data Minimization Compliance NeurIPS 2021 A Unified Approach to Interpreting and Boosting Adversarial Transferability ICLR 2021 A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents NAACL 2021 A Unified Taylor Framework for Revisiting Attribution Methods AAAI 2021 A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI Interaction IJCAI 2021 A universal probabilistic spike count model reveals ongoing modulation of neural variability NeurIPS 2021 Automated coherence measures fail to index thought disorder in individuals at risk for psychosis NAACL 2021 Automated triaging of head MRI examinations using convolutional neural networks MIDL 2021 Automatic Correction of Internal Units in Generative Neural Networks CVPR 2021 Automatic Fake News Detection: Are Models Learning to Reason? ACL 2021 Automatic Fake News Detection in Political Platforms - A Transformer-based Approach ACL 2021 Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema EMNLP 2021 Back to the basics with inclusion of clinical domain knowledge - A simple, scalable and effective model of Alzheimer’s Disease classification MLHC 2021 BACO: A Background Knowledge- and Content-Based Framework for Citing Sentence Generation ACL 2021 Banach Space Representer Theorems for Neural Networks and Ridge Splines JMLR 2021 Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information ICML 2021 Bayesian Deep Basis Fitting for Depth Completion With Uncertainty ICCV 2021 Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example AAAI 2021 BayLIME: Bayesian local interpretable model-agnostic explanations UAI 2021 Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration NeurIPS 2021 BennettNLP at SemEval-2021 Task 5: Toxic Spans Detection using Stacked Embedding Powered Toxic Entity Recognizer SemEval 2021