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
- DOJ’s Final Rule on Bulk Data Transfers: The First 180 Days
- California Governor Signs SB 351, Strengthening the State’s Corporate Practice of Medicine Doctrine
- No Remuneration Plus No "But-For" Causation (Between an Alleged Kickback and Claims Submitted to the Government) Means No FCA Violation, District Court Says
- Novel Lawsuits Allege AI Chatbots Encouraged Minors’ Suicides, Mental Health Trauma: Considerations for Stakeholders
- DOJ Creates Civil Division Enforcement & Affirmative Litigation Branch: Implications for Health Care and Beyond