Conversational AI is far from being a solved problem, but you don’t need to rely on third-party APIs to build great chat and voice apps.
In this talk we will live-code a useful, engaging conversational AI bot based entirely on machine learning. We’ll be using Rasa NLU & Rasa Core, which are open source libraries for building machine learning-based chatbots and voice assistants. We will teach our system how to hold multi-turn conversations by creating some initial training data, and then refine its behaviour by interacting with the system and providing feedback. We will cover the fundamentals of conversational AI, including the most important algorithms for intent classification, entity extraction, and dialogue management.
What will attendees learn: