← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7318 directly classified papers

Papers per year

Papers

A Diagnostic Study of Explainability Techniques for Text Classification EMNLP 2020
Analyzing Individual Neurons in Pre-trained Language Models EMNLP 2020
Probing Task-Oriented Dialogue Representation from Language Models EMNLP 2020
Understanding Neural Abstractive Summarization Models via Uncertainty EMNLP 2020
Robustness to Modification with Shared Words in Paraphrase Identification EMNLP 2020
Gradient-based Analysis of NLP Models is Manipulable EMNLP 2020
Rethinking Self-Attention: Towards Interpretability in Neural Parsing EMNLP 2020
A Cognitively Motivated Approach to Spatial Information Extraction EMNLP 2020
F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering EMNLP 2020
Assessing the Helpfulness of Learning Materials with Inference-Based Learner-Like Agent EMNLP 2020
Hypergraph Attention Networks for Multimodal Learning CVPR 2020
Cooling-Shrinking Attack: Blinding the Tracker With Imperceptible Noises CVPR 2020
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network CVPR 2020
Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? ACL 2020
Contextualizing Hate Speech Classifiers with Post-hoc Explanation ACL 2020
Towards Emotion-aided Multi-modal Dialogue Act Classification ACL 2020
Joint Modelling of Emotion and Abusive Language Detection ACL 2020
Efficient Estimation of Influence of a Training Instance EMNLP 2020
How well does surprisal explain N400 amplitude under different experimental conditions? EMNLP 2020
Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension EMNLP 2020
diagNNose: A Library for Neural Activation Analysis EMNLP 2020
Evaluating Attribution Methods using White-Box LSTMs EMNLP 2020
Discovering the Compositional Structure of Vector Representations with Role Learning Networks EMNLP 2020
The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? EMNLP 2020
Impact of Politically Biased Data on Hate Speech Classification EMNLP 2020