How to use inverted index in candidates generation tasks?

You wrote in material:

In practice, for large scale system (Facebook, Google), we don’t use Collaborative Filtering and prefer low latency method to get candidate. One example is to leverage Inverted Index (commonly used in Lucene, Elastic Search)

Could you provide some materials about how to use the Inverted index for those proposes?

Hi @Pavel4!

Some resources to learn about inverted index are:

Hope these help!