Method get_att_score

seq2seq_models.py:141–143

(self, hidden, encoder_hidden)

    # score = h^T W h^e = h dot (W h^e)
    # TODO: We need to implement different score models
    def get_att_score(self, hidden, encoder_hidden):
        score = self.attn(encoder_hidden)
        return torch.dot(hidden.view(-1), score.view(-1))