Interpretability

Verification and Repair of Neural Networks AAAI 2021 Versatile Verification of Tree Ensembles ICML 2021 Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization AAAI 2021 VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering CoNLL 2021 Weakly Supervised Named Entity Tagging with Learnable Logical Rules ACL 2021 What BERTs and GPTs know about your brand? Probing contextual language models for affect associations NAACL 2021 What Can a Generative Language Model Answer About a Passage? EMNLP 2021 What Changed? Interpretable Model Comparison IJCAI 2021 What Context Features Can Transformer Language Models Use? ACL 2021 What does BERT Learn from Arabic Machine Reading Comprehension Datasets? EACL 2021 What does LIME really see in images? ICML 2021 What is Your Article Based On? Inferring Fine-grained Provenance ACL 2021 What Makes a Scientific Paper be Accepted for Publication? EMNLP 2021 What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations EMNLP 2021 What’s in a Name? Answer Equivalence For Open-Domain Question Answering EMNLP 2021 What’s in the Box? Exploring the Inner Life of Neural Networks with Robust Rules ICML 2021 What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models EMNLP 2021 What Sounds “Right” to Me? Experiential Factors in the Perception of Political Ideology EACL 2021 What they do when in doubt: a study of inductive biases in seq2seq learners ICLR 2021 What Will it Take to Fix Benchmarking in Natural Language Understanding? NAACL 2021 When and Why a Model Fails? A Human-in-the-loop Error Detection Framework for Sentiment Analysis NAACL 2021 When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting NeurIPS 2021 Where and What? Examining Interpretable Disentangled Representations CVPR 2021 Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering ACL 2021 Who’s on First?: Probing the Learning and Representation Capabilities of Language Models on Deterministic Closed Domains CoNLL 2021