Interpretability

Detecting Persuasive Atypicality by Modeling Contextual Compatibility ICCV 2021 DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts ACL 2021 Diagnosing the First-Order Logical Reasoning Ability Through LogicNLI EMNLP 2021 DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues ICLR 2021 Differentiable Inductive Logic Programming for Structured Examples AAAI 2021 Difficulty-Aware Machine Translation Evaluation ACL 2021 Direct Exploitation of Attention Weights for Translation Quality Estimation EMNLP 2021 DirectProbe: Studying Representations without Classifiers NAACL 2021 Discovering Interpretable Latent Space Directions of GANs Beyond Binary Attributes CVPR 2021 Discretized Integrated Gradients for Explaining Language Models EMNLP 2021 Disentangled Representation Learning in Heterogeneous Information Network for Large-scale Android Malware Detection in the COVID-19 Era and Beyond AAAI 2021 Disentangling syntax and semantics in the brain with deep networks ICML 2021 DISK-CSV: Distilling Interpretable Semantic Knowledge with a Class Semantic Vector EACL 2021 Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution ACL 2021 Distribution-free uncertainty quantification for classification under label shift UAI 2021 Dodrio: Exploring Transformer Models with Interactive Visualization ACL 2021 Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica EMNLP 2021 Does BERT Pretrained on Clinical Notes Reveal Sensitive Data? NAACL 2021 Does Explainable Artificial Intelligence Improve Human Decision-Making? AAAI 2021 Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings EMNLP 2021 Does My Representation Capture X? Probe-Ably ACL 2021 Does She Wink or Does She Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models EACL 2021 Does Social Pressure Drive Persuasion in Online Fora? EMNLP 2021 Do Language Models Know the Way to Rome? EMNLP 2021 DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning EMNLP 2021