Interpretability

Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions? EACL 2021 Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing NAACL 2021 Ecco: An Open Source Library for the Explainability of Transformer Language Models ACL 2021 EDGE: Explaining Deep Reinforcement Learning Policies NeurIPS 2021 Editing a classifier by rewriting its prediction rules NeurIPS 2021 Editing Factual Knowledge in Language Models EMNLP 2021 Efficient Computation and Analysis of Distributional Shapley Values AISTATS 2021 Efficient Explanations from Empirical Explainers EMNLP 2021 Efficiently Explaining CSPs with Unsatisfiable Subset Optimization IJCAI 2021 Emotion-Infused Models for Explainable Psychological Stress Detection NAACL 2021 Energy-Based Open-World Uncertainty Modeling for Confidence Calibration ICCV 2021 Enhancing Factual Consistency of Abstractive Summarization NAACL 2021 Enhancing Interpretable Clauses Semantically using Pretrained Word Representation EMNLP 2021 Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations EMNLP 2021 Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience EMNLP 2021 ENTRUST: Argument Reframing with Language Models and Entailment NAACL 2021 Error Analysis and the Role of Morphology EACL 2021 Error Identification for Machine Translation with Metric Embedding and Attention EMNLP 2021 Estimating the Unique Information of Continuous Variables NeurIPS 2021 Evaluating Deception Detection Model Robustness To Linguistic Variation NAACL 2021 Evaluating Neural Model Robustness for Machine Comprehension EACL 2021 Evaluating Saliency Methods for Neural Language Models NAACL 2021 Evaluation of Similarity-based Explanations ICLR 2021 Evaluations and Methods for Explanation through Robustness Analysis ICLR 2021 Evaluation Scheme of Focal Translation for Japanese Partially Amended Statutes ACL 2021