a3_entity_network.py 文件源码

def output_module(self):
        """
        1.use attention mechanism between query and hidden states, to get weighted sum of hidden state. 2.non-linearity of query and hidden state to get label.
        input: query_embedding:[batch_size,embed_size], hidden state:[batch_size,block_size,hidden_size] of memory
        :return:y: predicted label.[]
        """
        # 1.use attention mechanism between query and hidden states, to get weighted sum of hidden state.
        # 1.1 get possibility distribution (of similiarity)
        p=tf.nn.softmax(tf.multiply(tf.expand_dims(self.query_embedding,axis=1),self.hidden_state)) #shape:[batch_size,block_size,hidden_size]<---query_embedding_expand:[batch_size,1,hidden_size]; hidden_state:[batch_size,block_size,hidden_size]
        # 1.2 get weighted sum of hidden state
        u=tf.reduce_sum(tf.multiply(p,self.hidden_state),axis=1) #shape:[batch_size,hidden_size]<----------([batch_size,block_size,hidden_size],[batch_size,block_size,hidden_size])

        # 2.non-linearity of query and hidden state to get label
        H_u_matmul=tf.matmul(u,self.H)+self.h_u_bias #shape:[batch_size,hidden_size]<----([batch_size,hidden_size],[hidden_size,hidden_size])
        activation=self.activation(self.query_embedding + H_u_matmul,scope="query_add_hidden")           #shape:[batch_size,hidden_size]
        activation = tf.nn.dropout(activation,keep_prob=self.dropout_keep_prob) #shape:[batch_size,hidden_size]
        y=tf.matmul(activation,self.R)+self.y_bias #shape:[batch_size,vocab_size]<-----([batch_size,hidden_size],[hidden_size,vocab_size])
        return y #shape:[batch_size,vocab_size]