Skip to content


Welcome to the manual of the Platform authoring Web application.

The authoring application is a workspace with an intuitive UI where users—data scientists, knowledge engineers, data analysts—, alone or in teams, create, tune and deploy language models that can either categorize texts or extract information from them.
This application is complementary to NL Flow, the application that makes models usable via an API by putting them inside document analysis workflows.

In addition to this, the application allows users to:

  • Manage thesauri with a powerful editor, with the possibility of creating language models capable of predicting the citations of thesaurus concepts in texts.
  • Create corpora of documents, for a discovery activity as an end in itself or to reuse corpora as libraries—for training or testing purposes—in model generation projects.
  • Explore the knowledge graphs for the available languages, to make discoveries that are useful for other project activities.
  • Create customized versions of a knowledge graph starting from the factory version.

This is the users manual for the application and is divided into two parts: