According to the original paper, the dimension of input to Encoder block is 500(200+300).
That means we should not change the dimension of word embedding and char embedding in "Embedding Layer" . We should use "Conv" at the start of "Encoder Layer" in order to map it to dimension.
According to the original paper, the dimension of input to Encoder block is 500(200+300). That means we should not change the dimension of word embedding and char embedding in "Embedding Layer" . We should use "Conv" at the start of "Encoder Layer" in order to map it to dimension.