问一下Parallel Attention和Position Attention的区别 about abinet HOT 8 OPEN

# e.g. d_model = 512, max_seq_len = seq_len_q = 25, vocab_size = 37
key2att = nn.Linear(d_model, d_model)
query2att = nn.Linear(d_model, d_model)
embedding = nn.Embedding(max_seq_len, d_model)
score = nn.Linear(d_model, 1)
classifier = nn.Linear(d_model, vocab_size)

# input is encoder_out
reading_order = torch.arange(max_seq_len, dtype=torch.long)
Q = embedding(reading_order)  # (max_seq_len, d_model)
K, V = encoder_out  # (batch_size, seq_len_k, d_model)

# 这里计算att_weight的过程很容易理解，和经典的attention模型比如ASTER的attention过程相同
######
att_q = key2att(Q).unsqueeze(0).unsqueeze(2)  # (1, seq_len_q, 1, d_model)
att_k = query2att(K).unsqueeze(1)  # (batch_size, 1, seq_len_k, d_model)
att_weight = score(torch.tanh(att_q + att_k)).squeeze(3)  # (batch_size, seq_len_q, seq_len_k)
######

att_weight = F.softmax(att_weight, dim=-1)
decoder_out = torch.bmm(att_weight, K)  # (batch_size, seq_len_q, d_model)
logits = classifier(decoder_out)  # (batch_size, seq_len_q, vicab_size)

# e.g. d_model = 512, max_seq_len = seq_len_q = 25, vocab_size = 37
embedding = nn.Embedding(max_seq_len, d_model)
w0 = nn.Linear(max_seq_len, seq_len_k)
wv = nn.Linear(d_model, d_model)
we = nn.Linear(d_model, max_seq_len)
classifier = nn.Linear(d_model, vocab_size)

# input is encoder_out
K, V = encoder_out  # (batch_size, seq_len_k, d_model)
reading_order = torch.arange(max_seq_len, dtype=torch.long)

# 如何理解下面这段计算att_weight的代码?
#####
reading_order = embedding(reading_order)  # (seq_len_q, d_model)
reading_order = reading_order.unsqueeze(0).expand(K.size(0), -1)  # (batch_size, seq_len_q, d_model)
t = w0(reading_order.permute(0, 2, 1))  # (batch_size, d_model, seq_len_q) ==> (batch_size, d_model, seq_len_k)
t = torch.tanh(t.permute(0, 2, 1) + wv(K))  # (batch_size, seq_len_k, d_model)
att_weight = we(t)  # (batch_size, seq_len_k, d_model) ==> (batch_size, seq_len_k, seq_len_q)
######

att_weight = F.softmax(att_weight, dim=-1)
decoder_out = torch.bmm(att_weight, K)  # (batch_size, seq_len_q, d_model)
logits = classifier(decoder_out)  # (batch_size, seq_len_q, vicab_size)