Probabilities will be logged onto our two labels English and Spanish on which our generated model will map a sparse BoW representation. In the vocabulary, we will assign each word as an index. Let's say for example, we have two words in our vocabulary, that is hello and world, which have indices as zero and one, respectively. For example, for the sentence hello hello hello hello hello, the BoW vector is [5,0]. Similarly the BoW vector for hello world world hello world is [2,3], and so on.
Generally, it is [Count(hello),Count(world)].
Let us denote is BOW vector as x.
The network output is as follows:
Next, we need to pass the input through an affine map and then use log softmax:
data = [("El que lee ...
