model interpretability

Debiasing Concept-based Explanations with Causal Analysis ICLR 2021 Designing Counterfactual Generators using Deep Model Inversion NeurIPS 2021 Discretized Integrated Gradients for Explaining Language Models EMNLP 2021 Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica EMNLP 2021 Do Input Gradients Highlight Discriminative Features? NeurIPS 2021 Efficient Explanations from Empirical Explainers EMNLP 2021 Emotion-Infused Models for Explainable Psychological Stress Detection NAACL 2021 Evaluating Saliency Methods for Neural Language Models NAACL 2021 Explainable Person Re-Identification With Attribute-Guided Metric Distillation ICCV 2021 Explaining Latent Representations with a Corpus of Examples NeurIPS 2021 Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks NAACL 2021 Explanation Consistency Training: Facilitating Consistency-Based Semi-Supervised Learning with Interpretability AAAI 2021 Exploratory Model Analysis Using Data-Driven Neuron Representations EMNLP 2021 Exploring Neural Language Models via Analysis of Local and Global Self-Attention Spaces EACL 2021 Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection ACL 2021 Foundations of Symbolic Languages for Model Interpretability NeurIPS 2021 Generative Causal Explanations for Graph Neural Networks ICML 2021 Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation ACL 2021 HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection AAAI 2021 Human Rationales as Attribution Priors for Explainable Stance Detection EMNLP 2021 Improving Deep Learning Interpretability by Saliency Guided Training NeurIPS 2021 Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification ACL 2021 Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates EMNLP 2021 Interpreting Multivariate Shapley Interactions in DNNs AAAI 2021 IrEne: Interpretable Energy Prediction for Transformers ACL 2021