Artificial intelligence (AI) systems have a growing impact on people's lives on an every-day-level, thus it is fundamental to protect, control and understand the behavior and complexity of different models. Interpretability assists data scientists to explain, debug and validate their models, thus helping to build trust towards the model.

Interpret-Text, the innovative interpretability technique for Natural Language Processing (NLP) models has been developed by the community, and just has been announced at Microsoft Build 2020.

During this session, attendees will get an understanding about how to explain their models and then how to build a visualization dashboard that provides insights into their data, using different state-of-the-art explainers.