In transformer model; to incorporate positional information of texts the researchers have added a positional encoding to the model. How is positional encoding works? How positional encoding system learns position when varying length and types of text are passed at different time intervals.

Take these two input text

"She is my Queen" "Elizabeth is the queen of england"

How these inputs were passed to the transformer and what happens to those texts in positional encoding?

Please explain with less math and with more intuition behind it.


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.