diff --git a/paddle/fluid/API.spec b/paddle/fluid/API.spec
index 601fa9cc0abaf72369bb96eae361a235e054e200..515ace3640489edd2ec4f4f9dce802b521fc9ded 100644
--- a/paddle/fluid/API.spec
+++ b/paddle/fluid/API.spec
@@ -164,10 +164,10 @@ paddle.fluid.layers.crop ArgSpec(args=['x', 'shape', 'offsets', 'name'], varargs
 paddle.fluid.layers.rank_loss ArgSpec(args=['label', 'left', 'right', 'name'], varargs=None, keywords=None, defaults=(None,))
 paddle.fluid.layers.prelu ArgSpec(args=['x', 'mode', 'param_attr', 'name'], varargs=None, keywords=None, defaults=(None, None))
 paddle.fluid.layers.flatten ArgSpec(args=['x', 'axis', 'name'], varargs=None, keywords=None, defaults=(1, None))
-paddle.fluid.layers.sequence_enumerate ArgSpec(args=['input', 'win_size', 'pad_value', 'name'], varargs=None, keywords=None, defaults=(None,))
 paddle.fluid.layers.sequence_mask ArgSpec(args=['x', 'maxlen', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, 'int64', None))
 paddle.fluid.layers.stack ArgSpec(args=['x', 'axis'], varargs=None, keywords=None, defaults=(0,))
 paddle.fluid.layers.unstack ArgSpec(args=['x', 'axis', 'num'], varargs=None, keywords=None, defaults=(0, None))
+paddle.fluid.layers.sequence_enumerate ArgSpec(args=['input', 'win_size', 'pad_value', 'name'], varargs=None, keywords=None, defaults=(0, None))
 paddle.fluid.layers.data ArgSpec(args=['name', 'shape', 'append_batch_size', 'dtype', 'lod_level', 'type', 'stop_gradient'], varargs=None, keywords=None, defaults=(True, 'float32', 0, VarType.LOD_TENSOR, True))
 paddle.fluid.layers.open_recordio_file ArgSpec(args=['filename', 'shapes', 'lod_levels', 'dtypes', 'pass_num', 'for_parallel'], varargs=None, keywords=None, defaults=(1, True))
 paddle.fluid.layers.open_files ArgSpec(args=['filenames', 'shapes', 'lod_levels', 'dtypes', 'thread_num', 'buffer_size', 'pass_num', 'is_test'], varargs=None, keywords=None, defaults=(None, None, 1, None))
diff --git a/paddle/fluid/operators/sequence_enumerate_op.cc b/paddle/fluid/operators/sequence_enumerate_op.cc
index ae0241bd77a7de1e28d87e8c020a088b8d23ea93..58e48c228bb34814700fd0f7a3d62ef4b1a435dd 100644
--- a/paddle/fluid/operators/sequence_enumerate_op.cc
+++ b/paddle/fluid/operators/sequence_enumerate_op.cc
@@ -63,9 +63,9 @@ class SequenceEnumerateOpMaker : public framework::OpProtoAndCheckerMaker {
 Sequence Enumerate Operator.
 
 Generate a new sequence for the input index sequence, which enumerates all the
-sub-sequences with length win_size of the input. 
-The enumerated sequence has the same 1st dimension with variable input, and
-the 2nd dimension is win_size, padded by pad_value if necessary in generation.
+sub-sequences with length `win_size` of the input. 
+The enumerated sequence has the same 1st dimension with variable `input`, and
+the 2nd dimension is `win_size`, padded by `pad_value` if necessary in generation.
     
 Examples:
 Case 1:
diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py
index 5642c8c8ef99cb6f0d635acfb8507396e080ea23..9862a3fe1b483fc1f48c745d147abba3f3230c1a 100644
--- a/python/paddle/fluid/layers/nn.py
+++ b/python/paddle/fluid/layers/nn.py
@@ -5653,9 +5653,9 @@ def flatten(x, axis=1, name=None):
 def sequence_enumerate(input, win_size, pad_value=0, name=None):
     """
     Generate a new sequence for the input index sequence, which enumerates all the
-    sub-sequences with length win_size of the input. 
-    The enumerated sequence has the same 1st dimension with variable input, and
-    the 2nd dimension is win_size, padded by pad_value if necessary in generation.
+    sub-sequences with length `win_size` of the input. 
+    The enumerated sequence has the same 1st dimension with variable `input`, and
+    the 2nd dimension is `win_size`, padded by `pad_value` if necessary in generation.
     
     Examples:
     Case 1: