Question: In this problem, we will walk through how dot - product attention weights we introduced in class are calculated. Suppose we have a Sequence -
In this problem, we will walk through how dotproduct attention weights we introduced in class are calculated. Suppose we have a Sequence toSequence machine translation MT model from English to Dothraki, where the hidden states for the encoder and decoder RNNs have size of We input the English sentence Dragons eat apple too into the MT model, and below are the values of the hidden states we get from the model in the encoder.
Step by Step Solution
There are 3 Steps involved in it
1 Expert Approved Answer
Step: 1 Unlock
Question Has Been Solved by an Expert!
Get step-by-step solutions from verified subject matter experts
Step: 2 Unlock
Step: 3 Unlock
