Getting Started With Embeddings

Check out this tutorial with the Notebook Companion:

Understanding embeddings

An embedding is a numerical representation of a piece of information, for example, text, documents, images, audio, etc. The representation captures the semantic meaning of what is being embedded, making it robust for many industry applications.

Given the text "What is the main benefit of voting?", an embedding of the sentence could be represented in a vector space, for example, with a list of 384 numbers (for example, [0.84, 0.42, ..., 0.02]). Since this list captures the meaning, we can do exciting things, like calculating the distance between different embeddings to determine how well the meaning of two sentences matches.

Embeddings are not limited to text! You can also create an embedding of an image (for example, a list of 384 numbers) and compare it with a text embedding to determine if a sentence describes the image. This concept is under powerful systems for image search, classification, description, and more!

How are embeddings generated? The open-source library called Sentence Transformers allows you to create state-of-the-art embeddings from images and text for free. This blog shows an example with this library.

What are embeddings for?

"[...] once you understand this ML multitool (embedding), you'll be able to build everything from search engines to recommendation systems to chatbots and a whole lot more. You don't have to be a data scientist with ML expertise to use them, nor do you need a huge labeled dataset." - Dale Markowitz, Google Cloud.

Once a piece of information (a sentence, a document, an image) is embedded, the creativity starts; several interesting industrial applications use embeddings. E.g., Google Search uses embeddings to match text to text and text to images; Snapchat uses them to "serve the right ad to the right user at the right time"; and Meta (Facebook) uses them for their social search.