Interpretability

Grammatical Error Correction Systems for Automated Assessment: Are They Susceptible to Universal Adversarial Attacks? AACL 2022 Graph Embeddings for Argumentation Quality Assessment EMNLP 2022 Grounding Meaning Representation for Situated Reasoning AACL 2022 GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games NeurIPS 2022 Guiding Neural Story Generation with Reader Models EMNLP 2022 HHP-Net: A Light Heteroscedastic Neural Network for Head Pose Estimation With Uncertainty WACV 2022 Hierarchical Attention Network for Explainable Depression Detection on Twitter Aided by Metaphor Concept Mappings COLING 2022 HiJoNLP at SemEval-2022 Task 2: Detecting Idiomaticity of Multiword Expressions using Multilingual Pretrained Language Models SemEval 2022 HINT: Hierarchical Neuron Concept Explainer CVPR 2022 How about Time? Probing a Multilingual Language Model for Temporal Relations COLING 2022 How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks ACL 2022 How Good Is Your Explanation? Algorithmic Stability Measures To Assess the Quality of Explanations for Deep Neural Networks WACV 2022 How Powerful are K-hop Message Passing Graph Neural Networks NeurIPS 2022 How Sampling Impacts the Robustness of Stochastic Neural Networks NeurIPS 2022 How to Find a Good Explanation for Clustering? AAAI 2022 How (Un)Faithful is Attention? EMNLP 2022 How Universal is Metonymy? Results from a Large-Scale Multilingual Analysis NAACL 2022 How Well Do Multi-hop Reading Comprehension Models Understand Date Information? AACL 2022 Human-AI Shared Control via Policy Dissection NeurIPS 2022 Human-Centered Evaluation of Explanations NAACL 2022 Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation EMNLP 2022 Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer ACL 2022 Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations for Model Predictions EMNLP 2022 i3Deep: Efficient 3D interactive segmentation with the nnU-Net MIDL 2022 Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models NAACL 2022