Recorded sessions here!

Missed a Session? Watch all sessions back at a later date

Workshop - Text Classification by Transfer learning with Deep Transformers - Depop

A talk by Oduwa Edo-Osagie
Data Scientist, Depop

Register to watch this content

By submitting your email you agree to the Terms of Service and Privacy Statement
Watch this content now

Categories covered by this talk

About this talk

Abstract: One of the recent powerful advancements in natural language processing is transfer learning. Transfer learning refers to a machine learning methodology where a sophisticated model which has been trained for a generic task can be “transferred” to another task. In this workshop, we will introduce the notion of deep transformers, looking specifically at the BERT architecture. We will then carry out some practical transfer learning to leverage a pertained BERT model from TensorflowHub to build our own text classifiers. At the end of the workshop. Attendees will not only be able to create text classifiers leveraging the power of BERT, but also obtain skills allowing to adapt other pretrained models available on TensorflowHub for their needs, transfer learning style.

Prerequisites: Modern python development environment (python >= 3.6, pip).

Level of technical knowledge: Familiarity with Python and at least a light understanding of neural networks. Some familiarity with Tensorflow and Keraswould also be useful, but not required.

Schedule GMT - 9:00AM Start - 10:30 AM Break - 12:00 PM Close

Have you got yours yet?

Our All-Access Passes are a must if you want to get the most out of this event.

Check them out

DSF Swag Bag

This session qualifies for a Swag Bag - INCLUDED IN BAG - DSF 2020 Bag - Notebook and Pen - 2020 Stickers (The Great Indoors) - Bottle Opener Keyring - Drink Coaster For info on how to redeem your bag please click the URL below

Please note, you need to register as an attendee before you can access this freebie.

Learn from amazing companies like these

Depop

Proudly supported by

Want to sponsor? Contact us to find out more.