the knowledge attention mask had not implemente in the code

[lyshuang]

Hi, it's my honor to read your paper. I'm very interested in your work.
But I found the knowledge attention mask mentioned in the paper has not implemente in your code. I just found as followings:
def prepare_attention_matrix(self, kg, weights): attention_mat = np.array((5,5)) return attention_mat
I don't know whether it was my negligence or what the reason was. I hope to receive your reply. Thanks.