← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7318 directly classified papers

Papers per year

Papers

Neural Utility Functions AAAI 2021
Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings EMNLP 2021
The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation EMNLP 2021
Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution IJCNLP 2021
Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks IJCNLP 2021
I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling IJCNLP 2021
More Identifiable yet Equally Performant Transformers for Text Classification IJCNLP 2021
Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation IJCNLP 2021
Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions AAAI 2021
Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression AISTATS 2021
An Analysis of LIME for Text Data AISTATS 2021
Investigating Feature Selection and Explainability for COVID-19 Diagnostics from Cough Sounds INTERSPEECH 2021
Raven's Progressive Matrices Completion with Latent Gaussian Process Priors AAAI 2021
What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations EMNLP 2021
A Hybrid Rule-Based and Neural Coreference Resolution System with an Evaluation on Dutch Literature EMNLP 2021
SeqScore: Addressing Barriers to Reproducible Named Entity Recognition Evaluation EMNLP 2021
On Explainability of Graph Neural Networks via Subgraph Explorations ICML 2021
SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks ICML 2021
Leveraging Sparse Linear Layers for Debuggable Deep Networks ICML 2021
Thinking Like Transformers ICML 2021
GANMEX: One-vs-One Attributions using GAN-based Model Explainability ICML 2021
Generative Causal Explanations for Graph Neural Networks ICML 2021
Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity ICML 2021
Re-understanding Finite-State Representations of Recurrent Policy Networks ICML 2021
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation ICML 2021