GPT 3

Let's Build a Language Translator! LIVE



Siraj Raval

The specific application of Machine Learning that has always interested me the most is Natural Language Processing. During this live game show, I’ll ask 3 NLP questions that you’ll need to answer interactively via a link i’ll provide. At the end, we’ll crown 1 winner. They’ll win $500 cash (sent via BTC or ), a freestyle rap performance by me, and early access to my coming game titled Code Royale. If we can get computers to understand and interpret human language as well as we do, then they’ll be capable of automating any intellectual task we can conceive of. Modern NLP curriculums incorporate probability, linear algebra, calculus, part linguistics, and even philosophy. We’re going to build a language translator from English to Sanskrit using various deep learning tools and discuss different modern methodologies we could use.

Please Subscribe! And Like. And Comment. That’s what keeps me going.

Answer live questions here:
https://itempool.com/llsourcell/live

Read through HuggingFace’s NLP docs to prepare yourself and come Tuesday, let the games begin:
https://github.com/huggingface

Learn Machine Learning in 3 Months for FREE:
https://www.youtube.com/watch/Cr6VqTRO1v0

Best Language Model doc:
http://www.cs.columbia.edu/~mcollins/lm-spring2013.pdf

Markov Chains:
https://www.sciencedirect.com/topics/mathematics/markov-process

Best Reformer illustration:
https://towardsdatascience.com/illustrating-the-reformer-393575ac6ba0

A collection of Sanskrit English projects to help you get started:
https://github.com/search?l=Jupyter+Notebook&q=sanskrit&type=Repositories

This week’s prize $ was sponsored by ClassPert (free search engine for courses):
https://classpert.com/