Interpretability

The Acceptability Delta Criterion: Testing Knowledge of Language using the Gradience of Sentence Acceptability EMNLP 2021 The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing ACL 2021 The Corpora They Are a-Changing: a Case Study in Italian Newspapers ACL 2021 The Curious Case of Hallucinations in Neural Machine Translation NAACL 2021 The effectiveness of feature attribution methods and its correlation with automatic evaluation scores NeurIPS 2021 The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results EMNLP 2021 The geometry of integration in text classification RNNs ICLR 2021 The Great Misalignment Problem in Human Evaluation of NLP Methods EACL 2021 The Heads Hypothesis: A Unifying Statistical Approach Towards Understanding Multi-Headed Attention in BERT AAAI 2021 The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation EMNLP 2021 The More Detail, the Better? – Investigating the Effects of Semantic Ontology Specificity on Vector Semantic Classification with a Plains Cree / nêhiyawêwin Dictionary NAACL 2021 The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations NeurIPS 2021 Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools EMNLP 2021 The Sparse Vector Technique, Revisited COLT 2021 The Tractability of SHAP-Score-Based Explanations for Classification over Deterministic and Decomposable Boolean Circuits AAAI 2021 The UMD Submission to the Explainable MT Quality Estimation Shared Task: Combining Explanation Models with Sequence Labeling EMNLP 2021 The Utility of Explainable AI in Ad Hoc Human-Machine Teaming NeurIPS 2021 Thinking Fast and Slow in AI AAAI 2021 Thinking Like Transformers ICML 2021 Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding EMNLP 2021 Topological Uncertainty: Monitoring Trained Neural Networks through Persistence of Activation Graphs IJCAI 2021 To Protect and To Serve? Analyzing Entity-Centric Framing of Police Violence EMNLP 2021 Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers NAACL 2021 Towards a Data Analytics Pipeline for the Visualisation of Complexity Metrics in L2 writings EACL 2021 Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR EACL 2021