diff --git a/mindspore/nn/probability/bijector/invert.py b/mindspore/nn/probability/bijector/invert.py
index d87f8d45d7..107e9b2df8 100644
--- a/mindspore/nn/probability/bijector/invert.py
+++ b/mindspore/nn/probability/bijector/invert.py
@@ -23,7 +23,7 @@ class Invert(Bijector):
 
     Args:
         bijector (Bijector): Base Bijector.
-        name (str): The name of the Bijector. Default: Invert.
+        name (str): The name of the Bijector. Default: 'Invert' + bijector.name.
 
     Supported Platforms:
         ``Ascend`` ``GPU``
@@ -55,10 +55,10 @@ class Invert(Bijector):
 
     def __init__(self,
                  bijector,
-                 name='Invert'):
+                 name=""):
         param = dict(locals())
         validator.check_value_type('bijector', bijector, [Bijector], "Invert")
-        name = (name + bijector.name) if name == 'Invert' else name
+        name = name or ('Invert' + bijector.name)
         super(Invert, self).__init__(is_constant_jacobian=bijector.is_constant_jacobian,
                                      is_injective=bijector.is_injective,
                                      name=name,
diff --git a/mindspore/nn/probability/distribution/bernoulli.py b/mindspore/nn/probability/distribution/bernoulli.py
index d579dc2356..28c4dff493 100644
--- a/mindspore/nn/probability/distribution/bernoulli.py
+++ b/mindspore/nn/probability/distribution/bernoulli.py
@@ -27,7 +27,7 @@ class Bernoulli(Distribution):
     Bernoulli Distribution.
 
     Args:
-        probs (float, list, numpy.ndarray, Tensor, Parameter): The probability of that the outcome is 1.
+        probs (float, list, numpy.ndarray, Tensor): The probability of that the outcome is 1.
         seed (int): The seed used in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.int32.
         name (str): The name of the distribution. Default: 'Bernoulli'.
diff --git a/mindspore/nn/probability/distribution/beta.py b/mindspore/nn/probability/distribution/beta.py
index 5868b40ee9..75fd7d65cc 100644
--- a/mindspore/nn/probability/distribution/beta.py
+++ b/mindspore/nn/probability/distribution/beta.py
@@ -29,9 +29,9 @@ class Beta(Distribution):
     Beta distribution.
 
     Args:
-        concentration1 (list, numpy.ndarray, Tensor, Parameter): The concentration1,
+        concentration1 (list, numpy.ndarray, Tensor): The concentration1,
           also know as alpha of the Beta distribution.
-        concentration0 (list, numpy.ndarray, Tensor, Parameter): The concentration0, also know as
+        concentration0 (list, numpy.ndarray, Tensor): The concentration0, also know as
           beta of the Beta distribution.
         seed (int): The seed used in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.float32.
@@ -154,9 +154,9 @@ class Beta(Distribution):
 
         # As some operators can't accept scalar input, check the type here
         if isinstance(concentration0, float):
-            raise TypeError("Parameter concentration0 can't be scalar")
+            raise TypeError("Input concentration0 can't be scalar")
         if isinstance(concentration1, float):
-            raise TypeError("Parameter concentration1 can't be scalar")
+            raise TypeError("Input concentration1 can't be scalar")
 
         super(Beta, self).__init__(seed, dtype, name, param)
 
diff --git a/mindspore/nn/probability/distribution/categorical.py b/mindspore/nn/probability/distribution/categorical.py
index b9c9eed47b..e1be1ab8e0 100644
--- a/mindspore/nn/probability/distribution/categorical.py
+++ b/mindspore/nn/probability/distribution/categorical.py
@@ -31,7 +31,7 @@ class Categorical(Distribution):
     Create a categorical distribution parameterized by event probabilities.
 
     Args:
-        probs (Tensor, list, numpy.ndarray, Parameter): Event probabilities.
+        probs (Tensor, list, numpy.ndarray): Event probabilities.
         seed (int): The global seed is used in sampling. Global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.int32.
         name (str): The name of the distribution. Default: Categorical.
diff --git a/mindspore/nn/probability/distribution/cauchy.py b/mindspore/nn/probability/distribution/cauchy.py
index 41ed2eaa0b..d0229f14ef 100644
--- a/mindspore/nn/probability/distribution/cauchy.py
+++ b/mindspore/nn/probability/distribution/cauchy.py
@@ -28,8 +28,8 @@ class Cauchy(Distribution):
     Cauchy distribution.
 
     Args:
-        loc (int, float, list, numpy.ndarray, Tensor, Parameter): The location of the Cauchy distribution.
-        scale (int, float, list, numpy.ndarray, Tensor, Parameter): The scale of the Cauchy distribution.
+        loc (int, float, list, numpy.ndarray, Tensor): The location of the Cauchy distribution.
+        scale (int, float, list, numpy.ndarray, Tensor): The scale of the Cauchy distribution.
         seed (int): The seed used in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.float32.
         name (str): The name of the distribution. Default: 'Cauchy'.
diff --git a/mindspore/nn/probability/distribution/exponential.py b/mindspore/nn/probability/distribution/exponential.py
index b71be7ff40..00d72c49e2 100644
--- a/mindspore/nn/probability/distribution/exponential.py
+++ b/mindspore/nn/probability/distribution/exponential.py
@@ -28,7 +28,7 @@ class Exponential(Distribution):
     Example class: Exponential Distribution.
 
     Args:
-        rate (float, list, numpy.ndarray, Tensor, Parameter): The inverse scale.
+        rate (float, list, numpy.ndarray, Tensor): The inverse scale.
         seed (int): The seed used in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.float32.
         name (str): The name of the distribution. Default: 'Exponential'.
diff --git a/mindspore/nn/probability/distribution/gamma.py b/mindspore/nn/probability/distribution/gamma.py
index 4741d36e35..0bbb7e7015 100644
--- a/mindspore/nn/probability/distribution/gamma.py
+++ b/mindspore/nn/probability/distribution/gamma.py
@@ -29,9 +29,9 @@ class Gamma(Distribution):
     Gamma distribution.
 
     Args:
-        concentration (list, numpy.ndarray, Tensor, Parameter): The concentration,
+        concentration (list, numpy.ndarray, Tensor): The concentration,
           also know as alpha of the Gamma distribution.
-        rate (list, numpy.ndarray, Tensor, Parameter): The rate, also know as
+        rate (list, numpy.ndarray, Tensor): The rate, also know as
           beta of the Gamma distribution.
         seed (int): The seed used in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.float32.
@@ -150,9 +150,9 @@ class Gamma(Distribution):
 
         # As some operators can't accept scalar input, check the type here
         if isinstance(concentration, (int, float)):
-            raise TypeError("Parameter concentration can't be scalar")
+            raise TypeError("Input concentration can't be scalar")
         if isinstance(rate, (int, float)):
-            raise TypeError("Parameter rate can't be scalar")
+            raise TypeError("Input rate can't be scalar")
 
         super(Gamma, self).__init__(seed, dtype, name, param)
 
diff --git a/mindspore/nn/probability/distribution/geometric.py b/mindspore/nn/probability/distribution/geometric.py
index ff914df87d..4f52e5a0c3 100644
--- a/mindspore/nn/probability/distribution/geometric.py
+++ b/mindspore/nn/probability/distribution/geometric.py
@@ -30,7 +30,7 @@ class Geometric(Distribution):
     when the first success is achieved.
 
     Args:
-        probs (float, list, numpy.ndarray, Tensor, Parameter): The probability of success.
+        probs (float, list, numpy.ndarray, Tensor): The probability of success.
         seed (int): The seed used in sampling. Global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.int32.
         name (str): The name of the distribution. Default: 'Geometric'.
diff --git a/mindspore/nn/probability/distribution/gumbel.py b/mindspore/nn/probability/distribution/gumbel.py
index 83406c7569..4cf6ef28e7 100644
--- a/mindspore/nn/probability/distribution/gumbel.py
+++ b/mindspore/nn/probability/distribution/gumbel.py
@@ -29,8 +29,8 @@ class Gumbel(TransformedDistribution):
     Gumbel distribution.
 
     Args:
-        loc (int, float, list, numpy.ndarray, Tensor, Parameter): The location of Gumbel distribution.
-        scale (int, float, list, numpy.ndarray, Tensor, Parameter): The scale of Gumbel distribution.
+        loc (int, float, list, numpy.ndarray, Tensor): The location of Gumbel distribution.
+        scale (int, float, list, numpy.ndarray, Tensor): The scale of Gumbel distribution.
         seed (int): the seed used in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): type of the distribution. Default: mstype.float32.
         name (str): the name of the distribution. Default: 'Gumbel'.
diff --git a/mindspore/nn/probability/distribution/log_normal.py b/mindspore/nn/probability/distribution/log_normal.py
index 7af51ec53a..991efb8347 100644
--- a/mindspore/nn/probability/distribution/log_normal.py
+++ b/mindspore/nn/probability/distribution/log_normal.py
@@ -28,8 +28,8 @@ class LogNormal(msd.TransformedDistribution):
     logarithm is normally distributed. It is constructed as the exponential transformation of a Normal distribution.
 
     Args:
-        loc (int, float, list, numpy.ndarray, Tensor, Parameter): The mean of the underlying Normal distribution.
-        scale (int, float, list, numpy.ndarray, Tensor, Parameter): The standard deviation of the underlying
+        loc (int, float, list, numpy.ndarray, Tensor): The mean of the underlying Normal distribution.
+        scale (int, float, list, numpy.ndarray, Tensor): The standard deviation of the underlying
           Normal distribution.
         seed (int): the seed used in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): type of the distribution. Default: mstype.float32.
diff --git a/mindspore/nn/probability/distribution/logistic.py b/mindspore/nn/probability/distribution/logistic.py
index 2330cbe6be..f0b71ec77f 100644
--- a/mindspore/nn/probability/distribution/logistic.py
+++ b/mindspore/nn/probability/distribution/logistic.py
@@ -28,8 +28,8 @@ class Logistic(Distribution):
     Logistic distribution.
 
     Args:
-        loc (int, float, list, numpy.ndarray, Tensor, Parameter): The location of the Logistic distribution.
-        scale (int, float, list, numpy.ndarray, Tensor, Parameter): The scale of the Logistic distribution.
+        loc (int, float, list, numpy.ndarray, Tensor): The location of the Logistic distribution.
+        scale (int, float, list, numpy.ndarray, Tensor): The scale of the Logistic distribution.
         seed (int): The seed used in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.float32.
         name (str): The name of the distribution. Default: 'Logistic'.
diff --git a/mindspore/nn/probability/distribution/normal.py b/mindspore/nn/probability/distribution/normal.py
index 70e28fa56e..dceeacf5a7 100644
--- a/mindspore/nn/probability/distribution/normal.py
+++ b/mindspore/nn/probability/distribution/normal.py
@@ -28,8 +28,8 @@ class Normal(Distribution):
     Normal distribution.
 
     Args:
-        mean (int, float, list, numpy.ndarray, Tensor, Parameter): The mean of the Normal distribution.
-        sd (int, float, list, numpy.ndarray, Tensor, Parameter): The standard deviation of the Normal distribution.
+        mean (int, float, list, numpy.ndarray, Tensor): The mean of the Normal distribution.
+        sd (int, float, list, numpy.ndarray, Tensor): The standard deviation of the Normal distribution.
         seed (int): The seed used in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.float32.
         name (str): The name of the distribution. Default: 'Normal'.
diff --git a/mindspore/nn/probability/distribution/poisson.py b/mindspore/nn/probability/distribution/poisson.py
index 4f10e517bd..b91ffa94f3 100644
--- a/mindspore/nn/probability/distribution/poisson.py
+++ b/mindspore/nn/probability/distribution/poisson.py
@@ -29,7 +29,7 @@ class Poisson(Distribution):
     Poisson Distribution.
 
     Args:
-        rate (list, numpy.ndarray, Tensor, Parameter): The rate of the Poisson distribution..
+        rate (list, numpy.ndarray, Tensor): The rate of the Poisson distribution..
         seed (int): The seed used in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.float32.
         name (str): The name of the distribution. Default: 'Poisson'.
@@ -123,7 +123,7 @@ class Poisson(Distribution):
 
         # As some operators can't accept scalar input, check the type here
         if isinstance(rate, (int, float)):
-            raise TypeError("Parameter rate can't be scalar")
+            raise TypeError("Input rate can't be scalar")
 
         super(Poisson, self).__init__(seed, dtype, name, param)
 
diff --git a/mindspore/nn/probability/distribution/uniform.py b/mindspore/nn/probability/distribution/uniform.py
index 09bd0269dc..a09fc146a2 100644
--- a/mindspore/nn/probability/distribution/uniform.py
+++ b/mindspore/nn/probability/distribution/uniform.py
@@ -28,8 +28,8 @@ class Uniform(Distribution):
     Example class: Uniform Distribution.
 
     Args:
-        low (int, float, list, numpy.ndarray, Tensor, Parameter): The lower bound of the distribution.
-        high (int, float, list, numpy.ndarray, Tensor, Parameter): The upper bound of the distribution.
+        low (int, float, list, numpy.ndarray, Tensor): The lower bound of the distribution.
+        high (int, float, list, numpy.ndarray, Tensor): The upper bound of the distribution.
         seed (int): The seed uses in sampling. The global seed is used if it is None. Default: None.
         dtype (mindspore.dtype): The type of the event samples. Default: mstype.float32.
         name (str): The name of the distribution. Default: 'Uniform'.