Presented By O'Reilly and Cloudera
Make Data Work
September 25–26, 2017: Training
September 26–28, 2017: Tutorials & Conference
New York, NY

Deep learning for understanding language and holding conversations

Alan Nichol (Rasa)
Artificial Intelligence, Machine Learning & Data Science
Location: 1A 06/07 Level: Intermediate
Secondary topics:  Deep learning, Hardcore Data Science
Average rating: ****.
(4.33, 3 ratings)

There’s a large body of research on machine learning-based dialogue, but most voice and chat systems in production are still implemented using a state machine and a set of rules. Alan Nichol offers an overview of Rasa’s applied AI research in language understanding and dialogue and explains how open source implementations bring the state of the art to thousands of developers.

Topics include:

  • Deep learning for understanding language: How much data do you need?
  • Transfer learning and word2vec
  • Interactive learning for machine teaching of complex dialogues
  • The gap between well-posed research problems in conversational AI and developer requirements
Photo of Alan Nichol

Alan Nichol


Alan Nichol is cofounder and CTO of leading open source conversational AI company Rasa, where he helps create the software that enables developers to build conversational software that really works. Rasa is trusted by thousands of developers in enterprises worldwide, including UBS, ERGO, and Helvetia. Alan has years of experience building AI-powered products in industry and is the author of the DataCamp course Building chatbots in Python. He was featured in Forbes’s 30 under 30 list. Alan holds a PhD in machine learning from the University of Cambridge.