Interpretability

Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors NAACL 2021 Triggering Failures: Out-of-Distribution Detection by Learning From Local Adversarial Attacks in Semantic Segmentation ICCV 2021 TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments AAAI 2021 TropEx: An Algorithm for Extracting Linear Terms in Deep Neural Networks ICLR 2021 TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation EMNLP 2021 tWT–WT: A Dataset to Assert the Role of Target Entities for Detecting Stance of Tweets NAACL 2021 Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition ACL 2021 Uncertainty-Driven Loss for Single Image Super-Resolution NeurIPS 2021 Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs ICLR 2021 Uncertainty Estimation in Autoregressive Structured Prediction ICLR 2021 Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-Tuning ACL 2021 Understanding and Interpreting the Impact of User Context in Hate Speech Detection NAACL 2021 Understanding Clinical Collaborations Through Federated Classifier Selection MLHC 2021 Understanding Failures of Deep Networks via Robust Feature Extraction CVPR 2021 Understanding Instance-based Interpretability of Variational Auto-Encoders NeurIPS 2021 Understanding Interlocking Dynamics of Cooperative Rationalization NeurIPS 2021 Understanding Patterns of Anorexia Manifestations in Social Media Data with Deep Learning NAACL 2021 Understanding Pre-Editing for Black-Box Neural Machine Translation EACL 2021 Understanding the Extent to which Content Quality Metrics Measure the Information Quality of Summaries CoNLL 2021 Unified Dual-view Cognitive Model for Interpretable Claim Verification ACL 2021 Unsupervised Extractive Summarization-Based Representations for Accurate and Explainable Collaborative Filtering ACL 2021 User Driven Model Adjustment via Boolean Rule Explanations AAAI 2021 Using Platform Models for a Guided Explanatory Diagnosis Generation for Mobile Robots IJCAI 2021 Variation and generality in encoding of syntactic anomaly information in sentence embeddings EMNLP 2021 Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing CVPR 2021