In this session, I will review my journey into rebuilding the "Related Stories" feature on Princeton.edu news articles using semantic search technologies. I'll discuss the basics of how semantic search works, how it differs from traditional search, and my approach in implementing a practical solution with the lowest amount of complexity. I'll discuss the iterative approach I took, first from developing a simple proof of concept, then iterating on it to refine the results.
This will be a mostly high level introductory session. There's some technical discussion. Everyone can learn something from this talk.
