Multi-modal Deep Learning for Complex Document Understanding with Doug Burdick

EPISODE 541
WATCH
Play Video
Join our list for notifications and early access to events

About this Episode

Today we’re joined by Doug Burdick, a principal research staff member at IBM Research. In a recent interview, Doug’s colleague Yunyao Li joined us to talk through some of the broader enterprise NLP problems she’s working on. One of those problems is making documents machine consumable, especially with the traditionally archival file type, the PDF. That’s where Doug and his team come in. In our conversation, we discuss the multimodal approach they’ve taken to identify, interpret, contextualize and extract things like tables from a document, the challenges they’ve faced when dealing with the tables and how they evaluate the performance of models on tables. We also explore how he’s handled generalizing across different formats, how fine-tuning has to be in order to be effective, the problems that appear on the NLP side of things, and how deep learning models are being leveraged within the group.

Connect with Doug
Read More

Thanks to our sponsor IBM

The IBM Institute for Business Value (IBV) delivers trusted business insights from our position at the intersection of technology and business, combining expertise from industry thinkers, leading academics, and subject matter experts with global research and performance data. The IBV thought leadership portfolio includes research deep dives, benchmarking and performance comparisons, and data visualizations that support business decision making across regions, industries and technologies.
IBM Logo

Related Episodes

Related Topics

More from TWIML

Leave a Reply

Your email address will not be published.