I am struggling to understand how word embedding works, especially how the embedding matrix $W$ and context matrix $W'$ are created/updated. I understand that in the Input we may have a one-hot encoding of a given word, and that in the output we may have the word the most likely to be nearby this word $x_i$

enter image description here

Would you have any very simple mathematical example?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.