Marco Tulio Correia Ribeiro

Code for "High-Precision Model-Agnostic Explanations" paper

marcotcr

Experiments for AAAI anchor paper

marcotcr

Beyond Accuracy: Behavioral Testing of NLP models with CheckList

marcotcr

Lime: Explaining the predictions of any machine learning classifier

marcotcr

Code for all experiments.

marcotcr

Code for "Semantically Equivalent Adversarial Rules for Debugging NLP Models"

marcotcr

Models built with TensorFlow

marcotcr