Presented By O’Reilly and Cloudera
Make Data Work
March 5–6, 2018: Training
March 6–8, 2018: Tutorials & Conference
San Jose, CA

Fast and effective natural language understanding

Mike Conover (SkipFlag)
5:10pm5:50pm Wednesday, March 7, 2018
Average rating: *****
(5.00, 4 ratings)

Who is this presentation for?

  • Software engineers, machine learning engineers, data scientists, data journalists, and hackers

Prerequisite knowledge

  • Familiarity with machine learning concepts and the challenges involved in productionizing machine learning workflows
  • A basic understanding of deep learning (useful but not required)

What you'll learn

  • Explore techniques to amplify your work with natural language

Description

Mike Conover offers an overview of the essential techniques for understanding and working with natural language, with a focus on approaches you can use straight away to better understand the people who matter most to your work. From off-the-shelf neural models that capture the essence of a passage to scrappy libraries that do far more than their share of heavy lifting, this session will help you cut to the chase in any project dealing with the complexities of human expression.

However, the whole operation is moot if users can’t work with these approaches on their own terms and in the spaces in which they live and do business, so Mike focuses on how people actually work with language. Building on a backbone of essential modeling and design patterns, Mike outlines an architectural foundation that helps you make the most of containerization and GPU compute and shares battle-hardened storage and parallelization patterns that have won the day time and time again. Taken together, these practical approaches to building natural language understanding systems will position you to start solving tough problems in a domain that will change the face of computing for years to come.

Photo of Mike Conover

Mike Conover

SkipFlag

Mike Conover is an AI engineer at SkipFlag, where he builds machine learning technologies that leverage the behavior and relationships of hundreds of millions of people. Previously, Mike led news relevance research and development at LinkedIn. His work has appeared in the New York Times and the Wall Street Journal and on National Public Radio. Mike holds a PhD in complex systems analysis with a focus on information propagation in large-scale social networks.