Interpretability

ProtoX: Explaining a Reinforcement Learning Agent via Prototyping NeurIPS 2022 Provably expressive temporal graph networks NeurIPS 2022 Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression IJCAI 2022 Psycholinguistic Diagnosis of Language Models’ Commonsense Reasoning ACL 2022 (Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplification EMNLP 2022 Putting WordNet’s Dictionary Examples in the Context of Definition Modelling: An Empirical Analysis AACL 2022 QuaDUE-CCM: Interpretable Distributional Reinforcement Learning using Uncertain Contraction Metrics for Precise Quadrotor Trajectory Tracking CoRL 2022 Query and Attention Augmentation for Knowledge-Based Explainable Reasoning CVPR 2022 Questioning the Validity of Summarization Datasets and Improving Their Factual Consistency EMNLP 2022 Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English COLING 2022 Reason first, then respond: Modular Generation for Knowledge-infused Dialogue EMNLP 2022 Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality EMNLP 2022 Re-Examining Calibration: The Case of Question Answering EMNLP 2022 Region-Based Semantic Factorization in GANs ICML 2022 Region-dependent temperature scaling for certainty calibration and application to class-imbalanced token classification ACL 2022 Reinforcement Learning Explainability via Model Transforms (Student Abstract) AAAI 2022 Relating transformers to models and neural representations of the hippocampal formation ICLR 2022 Relevance for Robust Bayesian Network MAP-Explanations PGM 2022 Reliable Visualization for Deep Speaker Recognition Interspeech 2022 Repairing Neural Networks by Leaving the Right Past Behind NeurIPS 2022 Reproducibility in Computational Linguistics: Is Source Code Enough? EMNLP 2022 RES: An Interpretable Replicability Estimation System for Research Publications AAAI 2022 Results of WMT22 Metrics Shared Task: Stop Using BLEU – Neural Metrics Are Better and More Robust EMNLP 2022 Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain NeurIPS 2022 Rethinking Attention-Model Explainability through Faithfulness Violation Test ICML 2022