diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py
index e7e53bb53dfb872335713971a36dee4fdf5512e1..e95d43cae91f9613532868266533c258db9ec860 100644
--- a/python/paddle/fluid/layers/nn.py
+++ b/python/paddle/fluid/layers/nn.py
@@ -8063,13 +8063,13 @@ def bilinear_tensor_product(x,
     For example:
 
     .. math::
-       y_{i} = x * W_{i} * {y^\mathrm{T}}, i=0,1,...,K-1
+       out{i} = x * W_{i} * {y^\mathrm{T}}, i=0,1,...,size-1
 
     In this formular:
-      - :math:`x`: the first input contains M elements.
-      - :math:`y`: the second input contains N elements.
-      - :math:`y_{i}`: the i-th element of y.
+      - :math:`x`: the first input contains M elements, shape is [batch_size, M].
+      - :math:`y`: the second input contains N elements, shape is [batch_size, N].
       - :math:`W_{i}`: the i-th learned weight, shape is [M, N]
+      - :math:`out{i}`: the i-th element of out, shape is [batch_size, size].
       - :math:`y^\mathrm{T}`: the transpose of :math:`y_{2}`.
 
     The simple usage is:
@@ -8079,8 +8079,8 @@ def bilinear_tensor_product(x,
        tensor = bilinear_tensor_product(x=layer1, y=layer2, size=1000)
 
     Args:
-        x (Variable): 3-D input tensor with shape [N x M x P]
-        y (Variable): 3-D input tensor with shape [N x M x P]
+        x (Variable): 2-D input tensor with shape [batch_size, M]
+        y (Variable): 2-D input tensor with shape [batch_size, N]
         size (int): The dimension of this layer.
         act (str, default None): Activation to be applied to the output of this layer.
         name (str, default None): The name of this layer.
diff --git a/python/paddle/fluid/tests/unittests/test_layers.py b/python/paddle/fluid/tests/unittests/test_layers.py
index 49ba41e6fc908e9713414120bbeb45ca715042c3..a0d148bb7825a441d1b9f3e5a872d891b50816dc 100644
--- a/python/paddle/fluid/tests/unittests/test_layers.py
+++ b/python/paddle/fluid/tests/unittests/test_layers.py
@@ -901,6 +901,16 @@ class TestBook(unittest.TestCase):
             self.assertIsNotNone(data_1)
         print(str(program))
 
+    def test_bilinear_tensor_product_layer(self):
+        program = Program()
+        with program_guard(program):
+            data = layers.data(name='data', shape=[4], dtype="float32")
+
+            theta = layers.data(name="theta", shape=[5], dtype="float32")
+            out = layers.bilinear_tensor_product(data, theta, 6)
+
+        print(str(program))
+
 
 if __name__ == '__main__':
     unittest.main()