model interpretability

Understanding and Visualizing Deep Visual Saliency Models CVPR 2019 Universal Adversarial Triggers for Attacking and Analyzing NLP EMNLP 2019 Visualization and Interpretation of Latent Spaces for Controlling Expressive Speech Synthesis Through Audio Analysis Interspeech 2019 What Does This Word Mean? Explaining Contextualized Embeddings with Natural Language Definition EMNLP 2019 What made you do this? Understanding black-box decisions with sufficient input subsets AISTATS 2019 Adversarial TableQA: Attention Supervision for Question Answering on Tables ACML 2018 An Interactive Web-Interface for Visualizing the Inner Workings of the Question Answering LSTM EMNLP 2018 Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs ICLR 2018 Comparing Automatic and Human Evaluation of Local Explanations for Text Classification NAACL 2018 DALEX: Explainers for Complex Predictive Models in R JMLR 2018 Do explanations make VQA models more predictable to a human? EMNLP 2018 Explaining Deep Learning Models -- A Bayesian Non-parametric Approach NeurIPS 2018 Finding Influential Training Samples for Gradient Boosted Decision Trees ICML 2018 Human-in-the-Loop Interpretability Prior NeurIPS 2018 Interpreting Neural Network Hate Speech Classifiers EMNLP 2018 Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference EMNLP 2018 Learning Explanations from Language Data EMNLP 2018 Nonoverlap-Promoting Variable Selection ICML 2018 Portable, layer-wise task performance monitoring for NLP models EMNLP 2018 Understanding Convolutional Neural Networks for Text Classification EMNLP 2018 Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models EMNLP 2018 Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension EMNLP 2018 A Unified Approach to Interpreting Model Predictions NeurIPS 2017 Convolutional Neural Networks for Authorship Attribution of Short Texts EACL 2017 Understanding Black-box Predictions via Influence Functions ICML 2017