Building Contextual AI Assistants with Machine Learning and Open Source Tools

Justina Petraityte, Rasa

When built well, AI assistants provide great strategic business value and are fun to interact with. However, the majority of assistants built to this day are developed using just a set of rules and don’t go beyond simple FAQ interactions. This doesn’t scale in production and provides a rather disappointing user experience.

In this interactive talk, we will challenge the usual approach of chatbot development by introducing machine learning-based methods for dialogue management. You will learn the fundamentals of conversational AI, as well as machine learning techniques behind natural language and dialogue management. Finally, you will learn the basics of using Rasa Stack – an open source conversational framework.

Objective of the talk

  • Instead of writing rules, use machine learning and real conversational data to build AI assistants that scale.
  • It’s important to close the feedback loop and allow your assistants to learn from real user data.
  • OSS tools empower you to custom-tailor the frameworks you use to fit your domain.

Required audience experience

Fundamentals of machine learning are beneficial

You can view Christina’s slides below:

[email protected]

Track 3
Location: Burton and Redgrave Date: October 1, 2019 Time: 3:45 pm - 4:30 pm Justina Petraityte, Rasa Justina Petraityte, Rasa