We present AllenNLP Interpret, a toolkit built on top of AllenNLP for interactive model interpretations. The toolkit makes it easy to apply gradient-based saliency maps and adversarial attacks to new models, as well as develop new interpretation methods.

Don't forget to tag @eric-wallace in your comment, otherwise they may not be notified.

Ph.D. Student at Berkeley working on ML and NLP.
Share this project
Similar projects
A Survey of the State of Explainable AI for NLP
Overview of the operations and explainability techniques currently available for generating explanations for NLP model predictions.
Principles and Practice of Explainable Machine Learning
A survey to help industry practitioners understand the field of explainable machine learning better and apply the right tools.
Fairness and Machine Learning
This book gives a perspective on machine learning that treats fairness as a central concern rather than an afterthought.
G-MARC : GUI for Model Agnostic IML on Rupture risk Classifier
Study and Visualization of Model Agnostic Interpretable ML Approaches on the classification of Rupture status of Intracranial Aneurysms
Top collections