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
- NYDFS Cybersecurity Crackdown: New Requirements Now in Force, and "Covered Entities" Include HMOs, CCRCs—Are You Compliant?
- The Case for Regular Legal Maintenance: A Litigation Readiness Mindset for Modern Health Care Organizations
- The Rising Threats of Multi-Modal and Agentic AI in Cyber Attacks
- State Insurance Department Statements Scrutinize MA and MedSupp Unfair Trade Practices
- DOJ Subpoena Seeks Health Information of Hospital Patients Receiving Gender-Affirming Care: Will Judge Grant Motion to Quash?