HAN的attention里为什么加reduce_sum和reduce_max？
Author: fengdoudou1895Created Apr 21, 2020Updated May 20, 2020
在HAN的attention里面看到：
attetion_logits = tf.reduce_sum(hidden_state_context_similarity,axis = 2) attention_logits_max = tf.reduce_max(attention_logits, axis = 1,keep_dims = True) p_attention = tf.nn.softmax(attetion_logits-attention_logits_max)
原论文里没看到这个操作，请问这是为什么呢？
Source: brightmart/text_classification