Building contextual AI assistants with machine learning and open source tools

Tyler Dunn (Rasa)

13:45–14:25 Thursday, 17 October 2019

Location: King's Suite - Sandringham

Implementing AI

Secondary topics: Machine Learning tools, Text, Language, and Speech

Average rating:

(4.00, 4 ratings)

Download slides (PDF)

Who is this presentation for?

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

Level

Intermediate

Description

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.

Tyler Dunn challenges the usual approach of chatbot development by introducing machine learning-based methods for dialogue management. You’ll learn the fundamentals of conversational AI, machine learning techniques behind natural language and dialogue management, and the basics of using Rasa Stack—an open source ML-based framework that empowers developers to build contextual assistants in-house.

Prerequisite knowledge

A basic understanding of machine learning applications

What you'll learn

Learn machine learning models behind the NLU and dialogue management, techniques for training NLU models without pretrained word vectors, and best practices for gathering and preparing the training data and closing the feedback loop using real-time user feedback
Understand how to implement conversational assistants from scratch using open source tools Rasa NLU and Rasa Core

Tyler Dunn

Rasa

Ty Dunn is a product manager at Berlin-based startup Rasa, where he focuses on empowering developers to build the best possible conversational experiences and deploy them to production. Previously, Ty was a software engineer, most recently on a research team at another conversational AI startup. He’s interested in using this technology to improve how we process and respond to the increasing amount of information and complexity we face every day. Ty holds a BS in cognitive science with a focus in computation from the University of Michigan.