Hurtful Words, Quantifying Bices in Clinical Contextual Word Embeddings

Marzia Gershwin directs a research group at MIT's Computer Science and Artificial Intelligence Laboratory. One of the areas that I've really appreciated your work has been on algorithmic bias. We're all talking now about CHAT-GPT, but you were working on language models for many years before it came online. So maybe we could start with your paper titled, Hurtful Words, Quantifying Bices in Clinical Contextual Word Embeddings.