This post explores how bias can creep into word embeddings like word2vec, and I thought it might make it more fun (for me, at least) if I analyze a model trained on what you, my readers (all three of you), might have written.
Often when we talk about bias in word embeddings, we are talking about such things as bias against race or sex. But I’m going to talk about bias a little bit more generally to explore attitudes we have that are manifest in the words we use about any number of topics.
Blog Editors
Recent Updates
- First Circuit Clarifies When Clinical Labs Can Rely on Physician Orders
- Understanding the False Claims Act Statute of Limitations—and the Debate Over the “Last Overt Act” Rule
- Podcast: The Down-Low on Data for Value-Based Enterprises and Their Participating Providers – Diagnosing Health Care
- Second Circuit Affirms Denial of Preliminary Injunction in Challenge To N.Y. Law Restricting Weight Loss and Muscle Building Supplement Sales to Minors
- The DOJ’s Bulk Sensitive Data Rule and Your Obligation to “Know Your Data”