There's a large body of research on machine learning-based dialogue, but most voice and chat systems in production are still implemented using a state machine and a set of rules.

Rasa NLU & Rasa Core are the leading open source libraries for building machine learning-based chatbots and voice assistants.

In this workshop we will live-code a useful, engaging conversational AI bot based entirely on machine learning. We will start with language understanding, bootstrapping from very little annotated training data. You will then go on to build up your bot's ability to handle increasingly complex dialogues through supervised and interactive learning. What will attendees learn:

• deep dive into the Rasa NLU and Rasa Core open source libraries
• fundamentals of natural language understanding and dialogue management for building intelligent assistants
• overview of widely used algorithms
• good ways to manage training data

The code used in this tutorial can be found here: https://github.com/RasaHQ/rasa-workshop-pydata-berlin