Semantic Search: Measuring Meaning From Jaccard to Bert

submited by
Style Pass
2021-07-01 22:30:06

Similarity search is one of the fastest-growing domains in AI and machine learning. At its core, it is the process of matching relevant pieces of information together.

There’s a strong chance that you found this article through a search engine — most likely Google. Maybe you searched something like “what is semantic similarity search?” or “traditional vs vector similarity search”.

Google processed your query and used many of the same similarity search essentials that we will learn about in this article, to bring you to — this article.

If similarity search is at the heart of the success of a $1.65T company — the world’s fifth most valuable company in the world[1], there’s a good chance it’s worth learning more about.

In this article, we’ll cover a few of the most interesting — and powerful — of these techniques — focusing specifically on semantic search. We’ll learn how they work, what they’re good at, and how we can implement them ourselves.

Leave a Comment