The embedding vector value for both startseq and endseq will be a 50 dim zero vector. How will the model differentiate between startseq and endseq?
Embedding vector value for startseq and endseq
Hey @raunaqsingh10, if you will see carefully our model has no need to differentiate between startseq and endseq. Suppose training example is “kite is flying”, Than number of training examples formed,
startseq --paddings-- | Kite
startseq kite --paddings-- | is
startseq kite is --paddings-- | flying
startseq kite is flying --padding-- | endseq.
There is no training further training example which means there is no example in which startseq and endseq both occurs, in the xtrain. As soon as model predicts endseq, we break the furthere sentence formation.
Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. 
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.