querysum_model.py 文件源码

def _attention(self, prev_decoder_state, prev_embedding):
        with tf.variable_scope('attention') as scope:
            # e = score of shape [batch_size, output_seq_length, input_seq_length], e_{ij} = score(s_{i-1}, h_j)
            # e_i = score of shape [batch_size, input_seq_length], e_ij = score(prev_decoder_state, h_j)
            e_i = self._score(prev_decoder_state, prev_embedding)

            # alpha_i = softmax(e_i) of shape [batch_size, input_seq_length]
            alpha_i = tf.nn.softmax(e_i)

            resized_alpha_i = tf.reshape(tf.tile(alpha_i, [1, self.encoder_output_size]),
                                         [self.batch_size, -1, self.encoder_output_size])

            if self.mode == 'decode':
                c_i = tf.reduce_sum(tf.multiply(resized_alpha_i, self.pre_computed_encoder_states_placeholder), axis=1)
            else:
                c_i = tf.reduce_sum(tf.multiply(resized_alpha_i, self.encoder_outputs), axis=1)
            return c_i, e_i