In this episode, we are talking with Paul Azunre. Paul is one of the world’s experts in the area of Transfer Learning for NLP and is also an author of the upcoming book Transfer Learning for NLP published by Manning Publications. In this episode we talk about things such as:
1) Paul’s background and how his background in maths and optimization as well as fake news detection got him started in transfer learning in NLP.
3) High level summary of transfer learning in both computer vision and NLP and why this is the ImageNet moment of NLP.
4) Why ML and NLP practitioners today should be excited about transfer learning (such as how students in Ghana are able to build their own Google Translate using transfer learning)
5) How BERT, ELMo and ALBERT work at the high level and how they differ from traditional techniques like Word2Vec or FastText.
6) Differences between BERT, ELMo and ALBERT.
7) What makes Paul’s new book a must-read for anyone interested in this field.
✨Paul's Info👇
Paul’s Website: azunre.com (with all social media handles)
✨Chance for one of 2 free copies of Transfer Learning for NLP 🎉
Get a chance to win the free copy of Paul's book! Please share this episode on Twitter and add my Twitter handle "sanket107" to it, you will get a chance to win one of 2 free books. My Twitter: https://twitter.com/sanket107
✨Discount Code for all Manning Publications books! 🎊🤩
Special Link to get extra discount for Paul’s book:
As The Data Life Podcast listeners, you can also go to this link http://www.manning.com/?a_aid=Omnilence to get any Manning book with 40% discount with the code: poddlife20
This will help support this show as well and is much appreciated.
Thank you Manning Publications and Paul as well as sponsors to make this show a reality.
~Thanks for listening~