diff --git a/08.machine_translation/README.cn.md b/08.machine_translation/README.cn.md
index 81d268a7fc4000cde43934d931c6ad9eeee284da..5833fee8b448315f88fb546cfde32b7df7bb77c0 100644
--- a/08.machine_translation/README.cn.md
+++ b/08.machine_translation/README.cn.md
@@ -173,6 +173,7 @@ $$e_{ij} = {align(z_i, h_j)}$$
 # 加载 paddle的python包
 import sys
 import paddle.v2 as paddle
+import numpy as np
 
 # 配置只使用cpu，并且使用一个cpu进行训练
 paddle.init(use_gpu=False, trainer_count=1)
@@ -273,11 +274,11 @@ is_generating = False
             output_mem=decoder_mem,
             size=decoder_size)
 
-        out = paddle.layer.mixed(
+        out = paddle.layer.fc(
             size=target_dict_dim,
             bias_attr=True,
             act=paddle.activation.Softmax(),
-            input=paddle.layer.full_matrix_projection(input=gru_step))
+            input=gru_step)
         return out
    ```
 
@@ -325,7 +326,7 @@ is_generating = False
 
 6. 生成模式下的解码器调用：
 
-   - 首先，在序列生成任务中，由于解码阶段的RNN总是引用上一时刻生成出的词的词向量，作为当前时刻的输入，因此，使用`GeneratedInput`来自动完成这一过程。具体说明可见[GeneratedInput文档](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/howto/deep_model/rnn/recurrent_group_cn.md#输入)。
+   - 首先，在序列生成任务中，由于解码阶段的RNN总是引用上一时刻生成出的词的词向量，作为当前时刻的输入，因此，使用`GeneratedInput`来自动完成这一过程。具体说明可见[GeneratedInput文档](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/v2/howto/rnn/recurrent_group_cn.md#输入)。
    - 其次，使用`beam_search`函数循环调用`gru_decoder_with_attention`函数，生成出序列id。
 
    ```python
diff --git a/08.machine_translation/README.md b/08.machine_translation/README.md
index 45d7e19a3fc85afa0e9cdc936226aa7b5d1d9aed..d04d08777bb11839dbc61e748ed41e85fa861b11 100644
--- a/08.machine_translation/README.md
+++ b/08.machine_translation/README.md
@@ -215,6 +215,7 @@ This subset has 193319 instances of training data and 6003 instances of test dat
 ```python
 import sys
 import paddle.v2 as paddle
+import numpy as np
 
 # train with a single CPU
 paddle.init(use_gpu=False, trainer_count=1)
@@ -326,7 +327,7 @@ is_generating = False
         return out
    ```
 
-4. Define the name for the decoder and the first two input for `gru_decoder_with_attention`. Note that `StaticInput` is used for the two inputs. Please refer to [StaticInput Document](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/v2/howto/rnn/recurrent_group_en.md#input) for more details.
+1. Define the name for the decoder and the first two input for `gru_decoder_with_attention`. Note that `StaticInput` is used for the two inputs. Please refer to [StaticInput Document](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/v2/howto/rnn/recurrent_group_cn.md#input) for more details.
 
     ```python
     decoder_group_name = "decoder_group"