Interpretability

Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity ICML 2021 Improving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks ICCV 2021 Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification ACL 2021 Improving uncertainty calibration of deep neural networks via truth discovery and geometric optimization UAI 2021 Incorporating Residual and Normalization Layers into Analysis of Masked Language Models EMNLP 2021 Increasing Robustness to Spurious Correlations using Forgettable Examples EACL 2021 Inducing Transformer’s Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks EMNLP 2021 Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations ICML 2021 Influence Decompositions For Neural Network Attribution AISTATS 2021 Influence Functions in Deep Learning Are Fragile ICLR 2021 Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates EMNLP 2021 Integrated Directional Gradients: Feature Interaction Attribution for Neural NLP Models ACL 2021 IntelliCAT: Intelligent Machine Translation Post-Editing with Quality Estimation and Translation Suggestion ACL 2021 Interacting Knowledge Sources, Inspection and Analysis: Case-studies on Biomedical text processing EMNLP 2021 Interacting with Explanations through Critiquing IJCAI 2021 Interpretability for Morphological Inflection: from Character-level Predictions to Subword-level Rules EACL 2021 Interpretability Rules: Jointly Bootstrapping a Neural Relation Extractorwith an Explanation Decoder NAACL 2021 Interpretable Actions: Controlling Experts with Understandable Commands AAAI 2021 Interpretable agent communication from scratch (with a generic visual processor emerging on the side) NeurIPS 2021 Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making ACL 2021 Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes WACV 2021 Interpretable Compositional Convolutional Neural Networks IJCAI 2021 Interpretable Image Recognition by Constructing Transparent Embedding Space ICCV 2021 Interpretable Models for Granger Causality Using Self-explaining Neural Networks ICLR 2021 Interpretable NLG for Task-oriented Dialogue Systems with Heterogeneous Rendering Machines AAAI 2021