Interpretability

HILDIF: Interactive Debugging of NLI Models Using Influence Functions ACL 2021 HITMI&T at SemEval-2021 Task 5: Integrating Transformer and CRF for Toxic Spans Detection SemEval 2021 How Benign is Benign Overfitting ? ICLR 2021 How Certain is Your Transformer? EACL 2021 How Did This Get Funded?! Automatically Identifying Quirky Scientific Achievements ACL 2021 How Do BERT Embeddings Organize Linguistic Knowledge? NAACL 2021 How Does BERT Rerank Passages? An Attribution Analysis with Information Bottlenecks EMNLP 2021 How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings EMNLP 2021 How is BERT surprised? Layerwise detection of linguistic anomalies ACL 2021 How Well do Feature Visualizations Support Causal Understanding of CNN Activations? NeurIPS 2021 Human-Level Interpretable Learning for Aspect-Based Sentiment Analysis AAAI 2021 Human-Model Divergence in the Handling of Vagueness ACL 2021 Human Rationales as Attribution Priors for Explainable Stance Detection EMNLP 2021 Hybrid Predictive Models: When an Interpretable Model Collaborates with a Black-box Model JMLR 2021 HyDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks AAAI 2021 i-Algebra: Towards Interactive Interpretability of Deep Neural Networks AAAI 2021 Identifying regions of trusted predictions UAI 2021 Identifying untrustworthy predictions in neural networks by geometric gradient analysis UAI 2021 ID-Reveal: Identity-Aware DeepFake Video Detection ICCV 2021 If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques IJCAI 2021 ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation ACL 2021 Improved pronunciation prediction accuracy using morphology ACL 2021 Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning NeurIPS 2021 Improving Compositionality of Neural Networks by Decoding Representations to Inputs NeurIPS 2021 Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression AISTATS 2021