The Illustrated Word2vec - A Gentle Intro to Word Embeddings in Machine Learning

The concept of word embeddings is a central one in language processing (NLP). It's a method of representing words as numerically -- as lists of numbers that capture their meaning. Word2vec is an algorithm (a couple of algorithms, actually) of creating word vectors which helped popularize this concept. In this video, Jay take you in a guided tour of The Illustrated Word2Vec, an article explaining the method and how it came to be developed.
The article: jalammar.github.io/illustrate...
The talk: • Intuition & Use-Cases ...
Word2vec paper: proceedings.neurips.cc/paper/...
By Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean
---
Twitter: / jayalammar
Blog: jalammar.github.io/
Mailing List: jayalammar.substack.com/
---
More videos by Jay:
Language Processing with BERT: The 3 Minute Intro (Deep learning for NLP)
• Language Processing wi...
Explainable AI Cheat Sheet - Five Key Categories
• Explainable AI Cheat S...
The Narrated Transformer Language Model
• The Narrated Transform...

[@debbs_io]

I’ve watched a lot of videos on UA-cam. So many with animations etc. I nearly lost hope thinking I would never be able to grasp this concept. This is the only one that truly explains what the word embedding is and how it’s being derived in just a simple manner. Thank you so much

[@andrestellez84]

Thanks for these videos and your blog, I've learned so much from you. I always read your blog entries before dive in the original paper.

[@kaninlunaire3106]

Thank you for making this, Sir. It's very helpful!

[@MannyBernabe]

Personality scores is a great example!

[@nelsonpullella9977]

Great job! I enjoy very much your channel and blog! THK!

[@bagamanocnon]

jay, how does training LLMs differ from training text embedding models? or is an embedding model a byproduct of training an LLM? Like in transformers where text are converted to embeddings first before being fed to to the transformer blocks. Thanks!

[@lemoniall6553]

Very good explaination, one more thing, is word2vec using dimensional reduction too?, we can choose 50,100,200 dimensions? but how it works? Thanks

[@priyam66]

One unsolicited piece of advice. You got a profound knowledge of AI. You should share this knowledge by making more videos on several AI topics. I hope every AI aspirant gets a chance to watch your videos.
Keep it up..:)

[@sakaar-lok9109]

You are great, please never stop

[@abdikadermohamed5288]

Thank u so much its great Explanation clear understand

[@RoccoSwat]

This guy is the best. He is a good guy.

[@Shubham-su7sm]

Yoo Flying Beast!!

[@user-uf6ym4qx4c]

why are the person turning big and turning small all the time through the video?

[@sershsershsersh]

3:32 "...Jay is 38 on the 0 to 100 scale... so -.4 on the -1 to 1 scale...": How is that? I get -.24. If it's -.4 on the -1 to 1 scale, that's 30 on the 0 to 100 scale. Please fix my math.

[@TheCallToAdventure]

That’s what was bothering me too

[@AmarendraMahapatra]

i agree.. I thought to it as well

[@Udayanverma]

instead of explaining you went scrolling pages'. it was better if you have just kept it short and may be make other vid for subsequent sections.