Interpretability

Towards a more Robust Evaluation for Conversational Question Answering ACL 2021 Towards an Explainer-agnostic Conversational XAI IJCAI 2021 Towards a Theoretical Understanding of the Robustness of Variational Autoencoders AISTATS 2021 Towards Benchmarking the Utility of Explanations for Model Debugging NAACL 2021 Towards Better Explanations of Class Activation Mapping ICCV 2021 Towards Consumer Loan Fraud Detection: Graph Neural Networks with Role-Constrained Conditional Random Field AAAI 2021 Towards Detection and Remediation of Phonemic Confusion ACL 2021 Towards Extracting Graph Neural Network Models via Prediction Queries (Student Abstract) AAAI 2021 Towards Fair and Transparent Algorithmic Systems IJCAI 2021 Towards Human-Centered Summarization: A Case Study on Financial News EACL 2021 Towards Interpretable Deep Metric Learning With Structural Matching ICCV 2021 Towards Interpretable Deep Networks for Monocular Depth Estimation ICCV 2021 Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models NAACL 2021 Towards Multi-Grained Explainability for Graph Neural Networks NeurIPS 2021 Towards Objectively Evaluating the Quality of Generated Medical Summaries EACL 2021 Towards Quantifiable Dialogue Coherence Evaluation ACL 2021 Towards Rigorous Interpretations: a Formalisation of Feature Attribution ICML 2021 Towards robust vision by multi-task learning on monkey visual cortex NeurIPS 2021 Towards Scalable Complete Verification of Relu Neural Networks via Dependency-based Branching IJCAI 2021 Towards the Explainability of Multimodal Speech Emotion Recognition Interspeech 2021 Towards the Unification and Robustness of Perturbation and Gradient Based Explanations ICML 2021 To what extent do human explanations of model behavior align with actual model behavior? EMNLP 2021 ToxCCIn: Toxic Content Classification with Interpretability EACL 2021 Transformer Feed-Forward Layers Are Key-Value Memories EMNLP 2021 Transformer Interpretability Beyond Attention Visualization CVPR 2021