diff --git a/dssm/README.cn.md b/dssm/README.cn.md
index e1bd3cab89a2f76752c946b5a54cc250def9441b..e61e48b4a3eb635d4e8efa9ce45b08f8bb1bb56b 100644
--- a/dssm/README.cn.md
+++ b/dssm/README.cn.md
@@ -131,7 +131,7 @@ def create_cnn(self, emb, prefix=''):
 
     conv_3 = create_conv(3, self.dnn_dims[1], "cnn")
     conv_4 = create_conv(4, self.dnn_dims[1], "cnn")
-    return conv_3, conv_4
+    return paddle.layer.concat(input=[conv_3, conv_4])
 ```
 
 CNN 接受词向量序列，通过卷积和池化操作捕捉到原始句子的关键信息，最终输出一个语义向量（可以认为是句子向量）。
diff --git a/dssm/README.md b/dssm/README.md
index 8148ea6557183df1446b98ed6d3a4da1f92c6438..c4109ca5b556cd42fc286dbb889f36589aef332f 100644
--- a/dssm/README.md
+++ b/dssm/README.md
@@ -107,7 +107,7 @@ def create_cnn(self, emb, prefix=''):
 
     conv_3 = create_conv(3, self.dnn_dims[1], "cnn")
     conv_4 = create_conv(4, self.dnn_dims[1], "cnn")
-    return conv_3, conv_4
+    return paddle.layer.concat(input=[conv_3, conv_4])
 ```
 
 CNN accepts the word sequence of the embedding table, then process the data by convolution and pooling, and finally outputs a semantic vector.