Interpretability

SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency NAACL 2021 SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation ICML 2021 SpanPredict: Extraction of Predictive Document Spans with Neural Attention NAACL 2021 Spatio-Temporal Graph Scattering Transform ICLR 2021 SPECTRA: Sparse Structured Text Rationalization EMNLP 2021 Stanford MLab at SemEval-2021 Task 8: 48 Hours Is All You Need SemEval 2021 Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you? EMNLP 2021 Stroke Lesion Outcome Prediction Based on 4D CT Perfusion Data Using Temporal Convolutional Networks MIDL 2021 Strong Explanations in Abstract Argumentation AAAI 2021 Study of Manifestation of Civil Unrest on Twitter EMNLP 2021 Suicide Risk Prediction by Tracking Self-Harm Aspects in Tweets: NUS-IDS at the CLPsych 2021 Shared Task NAACL 2021 Summary Explorer: Visualizing the State of the Art in Text Summarization EMNLP 2021 Supporting Complaints Investigation for Nursing and Midwifery Regulatory Agencies ACL 2021 SWAG: Superpixels Weighted by Average Gradients for Explanations of CNNs WACV 2021 Symbol Grounding and Task Learning from Imperfect Corrections ACL 2021 Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models ACL 2021 TabNet: Attentive Interpretable Tabular Learning AAAI 2021 Targets and Aspects in Social Media Hate Speech ACL 2021 Teaching with Commentaries ICLR 2021 Telling BERT’s Full Story: from Local Attention to Global Aggregation EACL 2021 Test Harder than You Train: Probing with Extrapolation Splits EMNLP 2021 Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction ACL 2021 Text Counterfactuals via Latent Optimization and Shapley-Guided Search EMNLP 2021 Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models NAACL 2021 TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models ACL 2021