Interpretability

Learning to Explain: Generating Stable Explanations Fast ACL 2021 Learning to Predict Trustworthiness with Steep Slope Loss NeurIPS 2021 Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision AAAI 2021 Learning to Synthesize Programs as Interpretable and Generalizable Policies NeurIPS 2021 Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning NeurIPS 2021 Learning with Algorithmic Supervision via Continuous Relaxations NeurIPS 2021 Leveraging Sparse Linear Layers for Debuggable Deep Networks ICML 2021 Lifelong Explainer for Lifelong Learners EMNLP 2021 Linguistic Complexity Loss in Text-Based Therapy NAACL 2021 LMdiff: A Visual Diff Tool to Compare Language Models EMNLP 2021 LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking ACL 2021 LOA: Logical Optimal Actions for Text-based Interaction Games ACL 2021 Local Explanation of Dialogue Response Generation NeurIPS 2021 Local explanations via necessity and sufficiency: unifying theory and practice UAI 2021 Locally Valid and Discriminative Prediction Intervals for Deep Learning Models NeurIPS 2021 Locke’s Holiday: Belief Bias in Machine Reading EMNLP 2021 Low-Complexity Probing via Finding Subnetworks NAACL 2021 Machine versus Human Attention in Deep Reinforcement Learning Tasks NeurIPS 2021 Making a (Counterfactual) Difference One Rationale at a Time NeurIPS 2021 Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data ICML 2021 MARTA: Leveraging Human Rationales for Explainable Text Classification AAAI 2021 MEAN: Multi-head Entity Aware Attention Networkfor Political Perspective Detection in News Media NAACL 2021 Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation ACL 2021 Measuring Association Between Labels and Free-Text Rationales EMNLP 2021 Measuring the ‘I don’t know’ Problem through the Lens of Gricean Quantity NAACL 2021