Artificial Intelligence › Core AI ›

Interpretability

7318 directly classified papers

Papers per year

Papers

E-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks ICCV 2021

Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images ICCV 2021

Scalable Verification of Quantized Neural Networks AAAI 2021

What Context Features Can Transformer Language Models Use? ACL 2021

Keep CALM and Improve Visual Feature Attribution ICCV 2021

BACO: A Background Knowledge- and Content-Based Framework for Citing Sentence Generation ACL 2021

Pragmatic competence of pre-trained language models through the lens of discourse connectives EMNLP 2021

Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction EMNLP 2021

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction ACL 2021

Semantic Representation for Dialogue Modeling ACL 2021

Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation ACL 2021

Probing Pre-trained Language Models for Semantic Attributes and their Values EMNLP 2021

TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation EMNLP 2021

On the Tractability of SHAP Explanations AAAI 2021

The Tractability of SHAP-Score-Based Explanations for Classification over Deterministic and Decomposable Boolean Circuits AAAI 2021

Multi-Dimensional Explanation of Target Variables from Documents AAAI 2021

The Heads Hypothesis: A Unifying Statistical Approach Towards Understanding Multi-Headed Attention in BERT AAAI 2021

Fair and Interpretable Algorithmic Hiring using Evolutionary Many Objective Optimization AAAI 2021

Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution ACL 2021

Difficulty-Aware Machine Translation Evaluation ACL 2021

Is Sparse Attention more Interpretable? ACL 2021

Relative Importance in Sentence Processing ACL 2021

MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain ACL 2021

A Case Study of Analysis of Construals in Language on Social Media Surrounding a Crisis Event ACL 2021

ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering ACL 2021