Why Transformers Work (Natural Language Processing)

Why Transformers Work (Natural Language Processing)

Channel:
United States Coding Tech
Subscribers:
725,000
Published on ● Video Link: https://www.youtube.com/watch?v=QHkpGtDySqM


Duration: 44:07
3,823 views
136

This will be a technical talk where I'll explain the inner workings of the machine learning algorithms inside of Rasa. In particular I'll talk about why the transformer has become a part in many of our algorithms and has replaced RNNs. These include use-cases in natural language processing but also in dialogue handling.


You'll see a live demo of a typical error that an LSTM would make but a transformer wouldn't. The algorithms are explained with calm diagrams and very little maths.


PUBLICATION PERMISSIONS:
Original video was published with the Creative Commons Attribution license (reuse allowed). Link: https://www.youtube.com/watch?v=cFUSjztXbL8



Other Videos By Coding Tech


2021-02-20Translating Chinese Into Morse Code!
2021-02-1817 Things Developers Need to Know About Databases
2021-02-16WebAssembly: Digging a Bit Deeper
2021-02-08An introduction to WebAssembly
2021-02-07A Dev's Guide to CSS Grid
2021-02-07Hacking the Hybrid Cloud
2021-02-03Machine Learning for JavaScript Developers 101
2021-02-02New Performance Features: Make Your Pages Faster
2021-02-02VS Code and Data Science Tools
2021-02-01Blockchain Domains + IPFS = Decentralized Websites
2021-02-01Why Transformers Work (Natural Language Processing)
2021-02-01The Past, Present, and Future of CSS-in-JS
2021-01-29Parallel Processing in Python || Aaron Richter
2021-01-29Linux Memory Management at Scale
2021-01-27VS Code Productivity Tips and Tricks
2021-01-25.NET Productivity: Tips and Tricks
2021-01-24What Not to Do When Starting a New Project
2021-01-24The Future of Quantum Computing
2021-01-23What is Bitcoin and Blockchain (by Charles Hoskinson)
2021-01-23C++ As A Second Language
2021-01-19Mo'Problems, Mo'Nads


Tags:
machine learning
natural language processing
transformers