diff --git a/04.word2vec/README.md b/04.word2vec/README.md
index 352d3adf42de486d10afb389c5b4cda9f4e74977..a859d4845f7f6483f7e51c6ce24579bff6a7f994 100644
--- a/04.word2vec/README.md
+++ b/04.word2vec/README.md
@@ -203,7 +203,7 @@ First, load packages:
 
 from __future__ import print_function
 
-import paddle as paddle
+import paddle
 import paddle.fluid as fluid
 import six
 import numpy
@@ -214,13 +214,13 @@ import math
 Then, define the parameters:
 
 ```python
-EMBED_SIZE = 32 # embedding dimensions
+EMBED_SIZE = 32   # embedding dimensions
 HIDDEN_SIZE = 256 # hidden layer size
-N = 5 # ngram size, here fixed 5
-BATCH_SIZE = 100 # batch size
-PASS_NUM = 100 # Training rounds
+N = 5             # ngram size, here fixed 5
+BATCH_SIZE = 100  # batch size
+PASS_NUM = 100    # Training rounds
 
-use_cuda = False # Set to True if trained with GPU
+use_cuda = False  # Set to True if trained with GPU
 
 word_dict = paddle.dataset.imikolov.build_dict()
 dict_size = len(word_dict)
@@ -337,7 +337,7 @@ def train(if_use_cuda, params_dirname, is_sparse=True):
             accumulated = [
                 x[0] + x[1][0] for x in zip(accumulated, avg_cost_np)
             ]
-        count += 1
+            count += 1
         return [x / count for x in accumulated]
 
     def train_loop():
@@ -403,7 +403,7 @@ def infer(use_cuda, params_dirname=None):
         #Get the inference program using fluid.io.load_inference_model,
         #feed variable name by feed_target_names and fetch fetch_targets from scope
         [inferencer, feed_target_names,
-        fetch_targets] = fluid.io.load_inference_model(params_dirname, exe)
+         fetch_targets] = fluid.io.load_inference_model(params_dirname, exe)
 
         # Set the input and use 4 LoDTensor to represent 4 words. Each word here is an id,
         # Used to query the embedding table to get the corresponding word vector, so its shape size is [1].
diff --git a/04.word2vec/index.html b/04.word2vec/index.html
index c97cb748e3757045bc38158f607c5ad06671aee3..e907896843600f729b761b49f5c74ecd52a2fa8b 100644
--- a/04.word2vec/index.html
+++ b/04.word2vec/index.html
@@ -245,7 +245,7 @@ First, load packages:
 
 from __future__ import print_function
 
-import paddle as paddle
+import paddle
 import paddle.fluid as fluid
 import six
 import numpy
@@ -256,13 +256,13 @@ import math
 Then, define the parameters:
 
 ```python
-EMBED_SIZE = 32 # embedding dimensions
+EMBED_SIZE = 32   # embedding dimensions
 HIDDEN_SIZE = 256 # hidden layer size
-N = 5 # ngram size, here fixed 5
-BATCH_SIZE = 100 # batch size
-PASS_NUM = 100 # Training rounds
+N = 5             # ngram size, here fixed 5
+BATCH_SIZE = 100  # batch size
+PASS_NUM = 100    # Training rounds
 
-use_cuda = False # Set to True if trained with GPU
+use_cuda = False  # Set to True if trained with GPU
 
 word_dict = paddle.dataset.imikolov.build_dict()
 dict_size = len(word_dict)
@@ -379,7 +379,7 @@ def train(if_use_cuda, params_dirname, is_sparse=True):
             accumulated = [
                 x[0] + x[1][0] for x in zip(accumulated, avg_cost_np)
             ]
-        count += 1
+            count += 1
         return [x / count for x in accumulated]
 
     def train_loop():
@@ -445,7 +445,7 @@ def infer(use_cuda, params_dirname=None):
         #Get the inference program using fluid.io.load_inference_model,
         #feed variable name by feed_target_names and fetch fetch_targets from scope
         [inferencer, feed_target_names,
-        fetch_targets] = fluid.io.load_inference_model(params_dirname, exe)
+         fetch_targets] = fluid.io.load_inference_model(params_dirname, exe)
 
         # Set the input and use 4 LoDTensor to represent 4 words. Each word here is an id,
         # Used to query the embedding table to get the corresponding word vector, so its shape size is [1].
diff --git a/07.label_semantic_roles/README.md b/07.label_semantic_roles/README.md
index d84440ff2e4f922e3681ca346029a36de93dc594..4c804c4f1231e324cfa20ed414880488d1c891d9 100644
--- a/07.label_semantic_roles/README.md
+++ b/07.label_semantic_roles/README.md
@@ -208,17 +208,17 @@ print('pred_dict_len: ', pred_dict_len)
 
 ```python
 mark_dict_len = 2    # The dimension of the context area flag, which is a 0-1 2 value feature, so the dimension is 2
-Word_dim = 32        # Word vector dimension
-Mark_dim = 5         # The predicate context area is mapped to a real vector by the vocabulary, which is the adjacent dimension
-Hidden_dim = 512     # LSTM Hidden Layer Vector Dimensions : 512 / 4
-Depth = 8            # depth of stack LSTM
-Mix_hidden_lr = 1e-3 # Basic learning rate of fundamental_chain_crf layer
+word_dim = 32        # Word vector dimension
+mark_dim = 5         # The predicate context area is mapped to a real vector by the vocabulary, which is the adjacent dimension
+hidden_dim = 512     # LSTM Hidden Layer Vector Dimensions : 512 / 4
+depth = 8            # depth of stack LSTM
+mix_hidden_lr = 1e-3 # Basic learning rate of fundamental_chain_crf layer
 
 IS_SPARSE = True     # Whether to update embedding in sparse way
 PASS_NUM = 10        # Training epoches
 BATCH_SIZE = 10      # Batch size
 
-Embeddding_name = 'emb'
+embedding_name = 'emb'
 ```
 
 It should be specially noted that the parameter `hidden_dim = 512` actually specifies the dimension of the LSTM hidden layer's vector is 128. For this, please refer to the description of `dynamic_lstm` in the official PaddlePaddle API documentation.
diff --git a/07.label_semantic_roles/index.html b/07.label_semantic_roles/index.html
index 151ffb607c4f0c322369cbb3ee3c0c842352af42..16906208e6e9426e74344e06ce444d5eb5c89445 100644
--- a/07.label_semantic_roles/index.html
+++ b/07.label_semantic_roles/index.html
@@ -250,17 +250,17 @@ print('pred_dict_len: ', pred_dict_len)
 
 ```python
 mark_dict_len = 2    # The dimension of the context area flag, which is a 0-1 2 value feature, so the dimension is 2
-Word_dim = 32        # Word vector dimension
-Mark_dim = 5         # The predicate context area is mapped to a real vector by the vocabulary, which is the adjacent dimension
-Hidden_dim = 512     # LSTM Hidden Layer Vector Dimensions : 512 / 4
-Depth = 8            # depth of stack LSTM
-Mix_hidden_lr = 1e-3 # Basic learning rate of fundamental_chain_crf layer
+word_dim = 32        # Word vector dimension
+mark_dim = 5         # The predicate context area is mapped to a real vector by the vocabulary, which is the adjacent dimension
+hidden_dim = 512     # LSTM Hidden Layer Vector Dimensions : 512 / 4
+depth = 8            # depth of stack LSTM
+mix_hidden_lr = 1e-3 # Basic learning rate of fundamental_chain_crf layer
 
 IS_SPARSE = True     # Whether to update embedding in sparse way
 PASS_NUM = 10        # Training epoches
 BATCH_SIZE = 10      # Batch size
 
-Embeddding_name = 'emb'
+embedding_name = 'emb'
 ```
 
 It should be specially noted that the parameter `hidden_dim = 512` actually specifies the dimension of the LSTM hidden layer's vector is 128. For this, please refer to the description of `dynamic_lstm` in the official PaddlePaddle API documentation.