Through hands-on interaction with word-embedding, a widespread building block of many machine learning models working with human languages, we will explore the issues of bias and fairness in machine learning.
Introduction and setup
Intro to Natural Language Processing (NLP)
How to represent a language in computing?
Intro to word embeddings
Gender bias in word embeddings
Bias mitigation
Critical review
Hands-on exercises
Wrap-up: Takeaways and resources