Interpretability

Robustness Gym: Unifying the NLP Evaluation Landscape NAACL 2021 RuSentEval: Linguistic Source, Encoder Force! EACL 2021 Saliency is a Possible Red Herring When Diagnosing Poor Generalization ICLR 2021 Scalable Partial Explainability in Neural Networks via Flexible Activation Functions (Student Abstract) AAAI 2021 Scalable Verification of Quantized Neural Networks AAAI 2021 Scaling Symbolic Methods using Gradients for Neural Model Explanation ICLR 2021 SCOUTER: Slot Attention-Based Classifier for Explainable Image Recognition ICCV 2021 Screening Gender Transfer in Neural Machine Translation EMNLP 2021 Self-Attention Attribution: Interpreting Information Interactions Inside Transformer AAAI 2021 SELFEXPLAIN: A Self-Explaining Architecture for Neural Text Classifiers EMNLP 2021 Self-Supervised Attention-Aware Reinforcement Learning AAAI 2021 Self-supervised Out-of-distribution Detection for Cardiac CMR Segmentation MIDL 2021 Semantic Representation for Dialogue Modeling ACL 2021 SeqScore: Addressing Barriers to Reproducible Named Entity Recognition Evaluation EMNLP 2021 Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving ACL 2021 Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations EMNLP 2021 Shapley explainability on the data manifold ICLR 2021 Shapley Flow: A Graph-based Approach to Interpreting Model Predictions AISTATS 2021 SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks ICML 2021 Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection NeurIPS 2021 SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models AAAI 2021 Sketching curvature for efficient out-of-distribution detection for deep neural networks UAI 2021 SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis ACL 2021 “Something Something Hota Hai!” An Explainable Approach towards Sentiment Analysis on Indian Code-Mixed Data EMNLP 2021 Sorting through the noise: Testing robustness of information processing in pre-trained language models EMNLP 2021