diff --git a/python/paddle/nn/functional/input.py b/python/paddle/nn/functional/input.py
index bf389717518ce2f844c3e5ae9c525b8edd121e20..b88a2b042ff48160c12aedcca6f12591c154cd0e 100644
--- a/python/paddle/nn/functional/input.py
+++ b/python/paddle/nn/functional/input.py
@@ -148,9 +148,7 @@ def embedding(x, weight, padding_idx=None, sparse=False, name=None):
         sparse(bool): The flag indicating whether to use sparse update. This parameter only
             affects the performance of the backwards gradient update. It is recommended to set
             True because sparse update is faster. But some optimizers does not support sparse update,
-            such as :ref:`api_optimizer_AdadeltaOptimizer` , :ref:`api_optimizer_AdamaxOptimizer` ,
-            :ref:`api_optimizer_DecayedAdagradOptimizer` , :ref:`api_optimizer_FtrlOptimizer` ,
-            :ref:`api_optimizer_LambOptimizer` and :ref:`api_optimizer_LarsMomentumOptimizer` .
+            such as :ref:`api_paddle_optimizer_adadelta_Adadelta` , :ref:`api_paddle_optimizer_adamax_Adamax` , :ref:`api_paddle_optimizer_lamb_Lamb`.
             In these cases, sparse must be False. Default: False.
         padding_idx(int|long|None): padding_idx needs to be in the interval [-weight.shape[0], weight.shape[0]).
             If :math:`padding\_idx < 0`, the :math:`padding\_idx` will automatically be converted
diff --git a/python/paddle/nn/layer/common.py b/python/paddle/nn/layer/common.py
index 60c846f9f76ec08197afb6f37c10c1a3027f69d9..86a6fae0d6857fa4f5817f7280e3ce24f0107655 100644
--- a/python/paddle/nn/layer/common.py
+++ b/python/paddle/nn/layer/common.py
@@ -1229,7 +1229,7 @@ class Embedding(layers.Layer):
     For specific usage, refer to code examples. It implements the function of the Embedding Layer.
     This layer is used to lookup embeddings vector of ids provided by :attr:`x` .
     It automatically constructs a 2D embedding matrix based on the
-    input :attr:`num_embeddings` and attr:`embedding_dim`.
+    input :attr:`num_embeddings` and :attr:`embedding_dim`.
 
     The shape of output Tensor is generated by appending an emb_size dimension to the
     last dimension of the input Tensor shape.
@@ -1241,9 +1241,9 @@ class Embedding(layers.Layer):
 
         Case 1:
 
-        input is a Tensor. padding_idx = -1
-            input.data = [[1, 3], [2, 4], [4, 127]
-            input.shape = [3, 2]
+        x is a Tensor. padding_idx = -1
+            x.data = [[1, 3], [2, 4], [4, 127]
+            x.shape = [3, 2]
         Given size = [128, 16]
         output is a Tensor:
             out.shape = [3, 2, 16]
@@ -1261,7 +1261,7 @@ class Embedding(layers.Layer):
     Parameters:
         num_embeddings (int): Just one element which indicate the size
             of the dictionary of embeddings.
-        embedding_dim:  Just one element which indicate the size of each embedding vector respectively.
+        embedding_dim (int):  Just one element which indicate the size of each embedding vector respectively.
         padding_idx(int|long|None): padding_idx needs to be in the interval [-num_embeddings, num_embeddings).
             If :math:`padding\_idx < 0`, the :math:`padding\_idx` will automatically be converted
             to :math:`vocab\_size + padding\_idx` . It will output all-zero padding data whenever lookup
@@ -1270,9 +1270,7 @@ class Embedding(layers.Layer):
         sparse(bool): The flag indicating whether to use sparse update. This parameter only
             affects the performance of the backwards gradient update. It is recommended to set
             True because sparse update is faster. But some optimizer does not support sparse update,
-            such as :ref:`api_optimizer_AdadeltaOptimizer` , :ref:`api_optimizer_AdamaxOptimizer` ,
-            :ref:`api_optimizer_DecayedAdagradOptimizer` , :ref:`api_optimizer_FtrlOptimizer` ,
-            :ref:`api_optimizer_LambOptimizer` and :ref:`api_optimizer_LarsMomentumOptimizer` .
+            such as :ref:`api_paddle_optimizer_adadelta_Adadelta` , :ref:`api_paddle_optimizer_adamax_Adamax` , :ref:`api_paddle_optimizer_lamb_Lamb`.
             In these case, sparse must be False. Default: False.
         weight_attr(ParamAttr): To specify the weight parameter property. Default: None, which means the
             default weight parameter property is used. See usage for details in :ref:`api_ParamAttr` . In addition,