Fueling innovative software
July 15-18, 2019
Portland, OR

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

1:30pm5:00pm Monday, July 15, 2019
Incorporating Artificial Intelligence
Location: Portland 252
Secondary topics:  AI Enhanced
Average rating: ****.
(4.25, 16 ratings)

Who is this presentation for?

  • Data scientists, machine learning engineers, developers, and product managers

Level

Intermediate

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.

Prerequisite knowledge

  • A working knowledge of Python
  • Familiarity with machine learning concepts

Materials or downloads needed in advance

What you'll learn

  • Learn the open source tools Rasa NLU and Rasa Core, fundamentals of the machine learning behind the conversational AI, and best practices for building AI assistants that scale in production
  • Hear tips for collecting and using real conversational data for the development of AI assistants
Photo of Justina Petraityte

Justina Petraityte

Rasa

Justina Petraityte is a developer advocate at Berlin-based startup Rasa, where she helps improve the developer experience in using open source software for conversational AI. Justina has a background in econometrics and data analytics, and her interests include chatbots, natural language processing, and open source. Her curiosity for data science and human-behavior analytics has taken her to many places and industries; over the past three years, she’s worked in the video gaming, fintech, and insurance industries.

Comments on this page are now closed.

Comments

Picture of Audra Carter
Audra Carter | SENIOR SPEAKER MANAGER
07/12/2019 5:07am PDT

Hi @Edie – you can fine them here: https://github.com/RasaHQ/workshop-rasax . They are also now added to the top of this page.

Edith Brooks | SENIOR R&D S&E, COMPUTER SCIENCE
07/12/2019 4:07am PDT

Are the course downloads available yet?

Picture of Craig Palmer
Craig Palmer | SR. WEB PRODUCER
07/11/2019 4:38am PDT

See what’s included with the Expo Plus pass. This tutorial is only included with the Gold & Silver passes.

Steve Braich | MACHINE TRANSLATION ENGINEER
07/11/2019 4:30am PDT

Can I attend this as a Expo Plus pass holder?