The Responsible AI Blog

The Language Interpretability Tool: Interactive analysis of NLP models

Mitigating the Liabilities of Artificial Intelligence in NLP

Biases in NLP datasets and how that is impacting model results

Lesson Learned annotating training data for healthcare NLP projects

In lessons learned annotating training data for healthcare NLP projects, will explain the best strategies for getting the training data you need, the mistakes you should be able to avoid...

Beyond Accuracy: Behavioral Testing of NLP Models with CheckList