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

800 800 The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

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.

Watch on Youtube

Thanks to our Sponsor!

Thanks to our friends at IBM for their continued support of the podcast, and their sponsorship of today’s show. IBM Logo With over 3,000 researchers across the globe, IBM Research is committed to turning fundamental research into impactful technologies that improves lives. Through research efforts like Project Debater, AI Fairness 360, and many more, IBM researchers continue to contribute to fundamental innovations in the field of artificial intelligence as well as practical applications for the technologies they develop.

To learn more about IBM’s interesting projects and the many ways they are working to solve today’s pressing needs, visit twimlai.com/ibm.

Connect with Doug!

Resources

Join Forces!

Leave a Reply

Your email address will not be published.