conftrace_

feature attribution

280 papers

Explore in graph

Also known as

FA

Co-occurring keywords

model interpretability (519) explainable ai (480) shapley value (206) model explanation (155) neural network (6616) text classification (6793) explainable artificial intelligence (130) neural network interpretability (114) integrated gradient (71) attribution method (79)

Papers

Improving Deep Learning Interpretability by Saliency Guided Training NIPS 2021
Self-Interpretable Model with Transformation Equivariant Interpretation NIPS 2021
Ecco: An Open Source Library for the Explainability of Transformer Language Models IJCNLP 2021
Learning to Explain: Generating Stable Explanations Fast IJCNLP 2021
Attention Flows are Shapley Value Explanations IJCNLP 2021
Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks NAACL 2021
Evaluating Saliency Methods for Neural Language Models NAACL 2021
Attention vs non-attention for a Shapley-based explanation method NAACL 2021
DANCE: Enhancing saliency maps using decoys ICML 2021
On Smoother Attributions using Neural Stochastic Differential Equations IJCAI 2021
On the Tractability of SHAP Explanations AAAI 2021
Learning to Explain: Generating Stable Explanations Fast ACL 2021
Attention Flows are Shapley Value Explanations ACL 2021
Ecco: An Open Source Library for the Explainability of Transformer Language Models ACL 2021
Contrastive Explanations for Model Interpretability EMNLP 2021
Discretized Integrated Gradients for Explaining Language Models EMNLP 2021
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations EMNLP 2021
Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools EMNLP 2021
The effectiveness of feature attribution methods and its correlation with automatic evaluation scores NIPS 2021
Neural Additive Models: Interpretable Machine Learning with Neural Nets NIPS 2021
Foundations of Symbolic Languages for Model Interpretability NIPS 2021
On Locality of Local Explanation Models NIPS 2021
Fast Axiomatic Attribution for Neural Networks NIPS 2021
Enhanced Regularizers for Attributional Robustness AAAI 2021
Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions AAAI 2021