Building AI assistants that scale using machine learning and open source tools

Description

AI assistants are getting a great deal of attention from the industry and in research. However, the majority of assistants are still developed using a state machine and a set of rules. That doesn’t scale in production.

Justina Petraityte takes a different approach to build an intelligent assistant without any predefined rules. Instead, using open source libraries Rasa NLU and Rasa Core, you’ll build an engaging and fully functional conversational assistant that learns by observing real conversations based on machine learning. You’ll learn the fundamentals of building conversational AI, the foundations of machine learning models behind the NLU and dialogue management, and best practices for preparing training data and developing intelligent AI assistants that scale in production.

Outline:

Stage 1: Natural language understanding (NLU)—You’ll start with language understanding, bootstrapping from very little annotated training data and tackle the challenges of going beyond pretrained word vectors for NLU and enabling the assistant to capture more than one intention per user input.

Stage 2: Dialogue management—You’ll use machine learning to build the AI assistant’s ability to handle increasingly complex multiturn dialogues based on the actual conversational data and enable the assistant to actually complete user-requested tasks by connecting the assistant to external APIs and using the knowledge of the outside world to steer the conversation.

Stage 3: Close the feedback loop—You’ll close the feedback loop by improving the performance of the assistant using interactive learning and real-time user feedback.