diff --git a/label_semantic_roles/README.en.md b/label_semantic_roles/README.en.md
index 4accfe0aac6eaf7c42b92e3ffaee145d9e8e92b3..b2a75cb03db3a2ef90a5b2a492fdac020507d396 100644
--- a/label_semantic_roles/README.en.md
+++ b/label_semantic_roles/README.en.md
@@ -440,15 +440,15 @@ trainer = paddle.trainer.SGD(cost=crf_cost,
 As mentioned in data preparation section, we will use CoNLL 2005 test corpus as training data set. `conll05.test()` outputs one training instance at a time. It will be shuffled, and batched into mini batches as input.
 
 ```python
-reader = paddle.reader.batched(
+reader = paddle.batch(
     paddle.reader.shuffle(
         conll05.test(), buf_size=8192), batch_size=20)
 ```
 
-`reader_dict` is used to specify relationship between data instance and layer layer. For example, according to following `reader_dict`, the 0th column of data instance produced by`conll05.test()` correspond to data layer named `word_data`.
+`feeding` is used to specify relationship between data instance and layer layer. For example, according to following `feeding`, the 0th column of data instance produced by`conll05.test()` correspond to data layer named `word_data`.
 
 ```python
-reader_dict = {
+feeding = {
     'word_data': 0,
     'ctx_n2_data': 1,
     'ctx_n1_data': 2,
@@ -478,7 +478,7 @@ trainer.train(
     reader=reader,
     event_handler=event_handler,
     num_passes=10000,
-    reader_dict=reader_dict)
+    feeding=feeding)
 ```
 
 ## Conclusion
diff --git a/label_semantic_roles/README.md b/label_semantic_roles/README.md
index a96d9604fc52661a388fd45a8bfcac099b6d4e1f..0bead4228652b1b781a9bfe5beccc3c483928ad4 100644
--- a/label_semantic_roles/README.md
+++ b/label_semantic_roles/README.md
@@ -409,11 +409,11 @@ reader = paddle.batch(
         conll05.test(), buf_size=8192), batch_size=20)
 ```
 
-通过`reader_dict`来指定每一个数据和data_layer的对应关系。 例如 下面`reader_dict`表示: `conll05.test()`产生数据的第0列对应`word_data`层的特征。
+通过`feeding`来指定每一个数据和data_layer的对应关系。 例如 下面`feeding`表示: `conll05.test()`产生数据的第0列对应`word_data`层的特征。
 
 
 ```python
-reader_dict = {
+feeding = {
     'word_data': 0,
     'ctx_n2_data': 1,
     'ctx_n1_data': 2,
@@ -443,7 +443,7 @@ trainer.train(
     reader=reader,
     event_handler=event_handler,
     num_passes=10000,
-    reader_dict=reader_dict)
+    feeding=feeding)
 ```
 
 ## 总结