Back

Speaker "David Talby" Details Back

 

Topic

Using NLP, machine learning & deep learning algorithms to extract meaning from text

Abstract

This talk covers the three main tasks required to build a system that can extract semantically meaningful facts from free text documents – like clinical notes, patent applications, research papers on customer service emails. Current systems can go beyond the traditional search and keyword matching capabilities, to enable much deeper inference at scale, and this talk focuses on algorithms and open source libraries that may that possible.

The talk walks through building a natural language annotations pipeline with domain-specific annotators, training machine learning models and applying those as annotators, and using deep learning to automatically expand and update taxonomies. Source code will be available online after the talk to enable you to learn and experiment further.

Profile

David Talby is a chief technology officer at Pacific AI, helping fast-growing companies apply big data and data science techniques to solve real-world problems in healthcare, life science, and related fields. David has extensive experience in building and operating web-scale data science and business platforms, as well as building world-class, Agile, distributed teams. Previously, he was with Microsoft’s Bing Group, where he led business operations for Bing Shopping in the US and Europe, and worked at Amazon both in Seattle and the UK, where he built and ran distributed teams that helped scale Amazon’s financial systems. David holds a PhD in computer science and master’s degrees in both computer science and business administration.