Social Biases in Text Representations and Their Mitigation

This course discusses social biases in text representations and their mitigation. The learning outcomes include understanding gender bias, biases in word embeddings, biases in Masked Language Models, and multi-lingual bias evaluation. The course teaches methods to identify and address biases in machine learning models. The intended audience for this course includes data scientists, machine learning practitioners, and individuals interested in natural language processing and bias mitigation in AI technologies.