Back

Speaker "David Talby" Details Back

 

Topic

Delivering Fair, Safe and Effective NLP Models with Open-Source Tools

Abstract

While there's a lot of work done on defining the risks, goals, and policies for Responsible AI, less is known about what you can apply today to build safe, fair, and reliable models. This session introduces the open-source nlptest library, with examples of using it in real-world NLP projects.
 
This session will cover three common model testing gaps. The first is robustness - testing & improving a model's ability to handle accidental or intentional minor changes in input that can uncover model fragility and failure points. The second is biase - testing that a model does not embody stereotypes regarding gender, race, nationality, or other properties. The third is fairness - testing that a model performs with similar accuracy across demographic groups, and that the test dataset has representation of these groups to enable reliable testing.
 
This session is intended for data science practitioners and leaders who need to know what they can & should do today to build NLP systems that work safety & correctly in the real world.

Profile

David Talby is a chief technology officer at John Snow Labs, helping healthcare & life science companies put AI to good use. David is the creator of Spark NLP – the world’s most widely used natural language processing library in the enterprise. He has extensive experience building and running web-scale software platforms and teams – in startups, for Microsoft’s Bing in the US and Europe, and to scale Amazon’s financial systems in Seattle and the UK. David holds a PhD in computer science and master’s degrees in both computer science and business administration.