Feed Annif a controlled vocabulary (subject headings, thesaurus or classification) and existing metadata - Annif then knows how to assign subjects for new documents!
Annif is built upon a combination of existing natural language processing and machine learning tools including Maui, fastText and Gensim. It is designed to be multilingual and it can support any subject vocabulary (in SKOS or a simple TSV format). It can be used either via a command-line interface or a microservice-style REST API. It also comes with a mobile web app that can analyse physical documents such as printed books.
The video demonstrates the first prototype of Annif which is no longer being maintained.