Presented By
O’Reilly + Intel AI
Put AI to Work
April 15-18, 2019
New York, NY

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

1:45pm5:15pm Tuesday, April 16, 2019
Implementing AI
Location: Mercury Rotunda
Secondary topics:  Deep Learning and Machine Learning tools, Text, Language, and Speech

Who is this presentation for?

Machine Learning Engineers, Data Scientists, Software Engineers, Product Managers



Prerequisite knowledge

Good to have: - Fundamentals of machine learning and its applications in natural language processing - Basics of programming in Python

Materials or downloads needed in advance

- Laptop - Python (version 3.6 preferred) - GitHub repository of the workshop

What you'll learn

The main ideas and skills attendees will learn: - Machine learning models behind the NLU and dialogue management - Techniques of training NLU models without pretrained word vectors - Best practices of gathering and preparing the training data - Best practices of closing the feedback look using real-time user feedback - Implementing conversational assistants from scratch using open source tools Rasa NLU and Rasa Core


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

In this workshop, you are going to take a different approach and build an intelligent assistant without any predefined rules. Instead, using open source libraries Rasa NLU and Rasa Core, you’ll build an assistant which learns by observing real conversations. At the end of this workshop, you will have built an engaging and fully functioning conversational assistant based entirely on machine learning. The workshop will consist of the following stages:

Stage 1: Natural language understanding. You will start with language understanding, bootstrapping from very little annotated training data. In this stage, you will also 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 will use machine learning to build the AI assistant’s ability to handle increasingly complex multi-turn dialogues based on the actual conversational data. You will also 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: Closing the feedback loop. In the last section, you will close the feedback loop by improving the performance of the assistant by using the interactive learning and a real-time user feedback.

The attendees of this workshop will learn the fundamentals of building conversational AI, the foundations of machine learning models behind the NLU and dialogue management, the best practices of preparing training data and developing intelligent AI assistants that scale in production.

Photo of Justina Petraityte

Justina Petraityte


Justina has a background in Econometrics and Data Analytics. Her curiosity for Data Science and human behaviour analytics has taken her to many places and industries – over the past three years she has been doing Data Science work across video gaming, fintech, insurance industries. Her interest in chatbots, natural language processing and open source has led her to Rasa, a Berlin-based conversational AI startup where she works as a Developer Advocate focusing on improving developer experience in using open source software for conversational AI.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)