diff --git a/paddle/operators/math/matmul.h b/paddle/operators/math/matmul.h
index 88341412fbc62cea9bb435326f0b31afb45e23f9..ae7f1fe9be5066a0ac0ac522849d481fc66a19be 100644
--- a/paddle/operators/math/matmul.h
+++ b/paddle/operators/math/matmul.h
@@ -49,7 +49,7 @@ class MatMulFunctor {
                      "The dimensions of X and Y must be the same, and both of "
                      "them should be %d-dimensional.",
                      dim_b.size());
-      // The front rank-2 dimensions are accumulated on the batch_count, and the
+      // The first rank-2 dimensions are accumulated on the batch_count, and the
       // last two dimensions are used for matrix multiplication.
       for (int j = 0; j < dim_a.size() - 2; ++j) {
         PADDLE_ENFORCE_EQ(dim_b[j], dim_a[j],
diff --git a/paddle/operators/matmul_op.cc b/paddle/operators/matmul_op.cc
index d395dfd81bb48921058ff2f08bbada057ccd73fe..3336978c8d8d94c69b986970274661a01ad2161d 100644
--- a/paddle/operators/matmul_op.cc
+++ b/paddle/operators/matmul_op.cc
@@ -51,7 +51,7 @@ class MatMulOp : public framework::OperatorWithKernel {
           "them should be %d-dimensional.",
           dim_x.size());
 
-      // The front rank-2 dimensions are accumulated on the batch_count, and the
+      // The first rank-2 dimensions are accumulated on the batch_count, and the
       // last two dimensions are used for matrix multiplication.
       for (int j = 0; j < dim_x.size() - 2; ++j) {
         PADDLE_ENFORCE_EQ(dim_y[j], dim_x[j],
@@ -196,7 +196,7 @@ The differences are:
 - When the rank of the input data is less than or equal to 3, it
   is similar to the `numpy.matmul` function.
 - When the rank of the input is greater than 3, the rank of X and
-  Y must be equal, and the front `rank - 2` dimensions must be equal.
+  Y must be equal, and the first `rank - 2` dimensions must be equal.
 - We add `transpose_X` and `transpose_Y` flags.
 
 Both the input `X` and `Y` can carry the LoD (Level of Details) information,
diff --git a/paddle/operators/matmul_op.h b/paddle/operators/matmul_op.h
index 4935db839cb4d8f0faed964c929363f7bfef697b..fe6a97465f8992281c909d4600bcfd8121d6a64a 100644
--- a/paddle/operators/matmul_op.h
+++ b/paddle/operators/matmul_op.h
@@ -138,7 +138,7 @@ class MatMulGradKernel : public framework::OpKernel<T> {
     }
 
     int batch_count = 0;
-    // The front rank-2 dimensions are accumulated on the batch_count, and the
+    // The first rank-2 dimensions are accumulated on the batch_count, and the
     // last two dimensions are used for matrix multiplication.
     if (x_dims.size() > 3) {
       batch_count = accumulate(x_dims.begin(), x_dims.end() - 2, 1,
diff --git a/python/paddle/v2/fluid/tests/test_matmul_op.py b/python/paddle/v2/fluid/tests/test_matmul_op.py
index 7151b1f5c804920b4d67ea6429b2c20afe704126..2dba25e17d3bf72563a44f629e94949302688b39 100644
--- a/python/paddle/v2/fluid/tests/test_matmul_op.py
+++ b/python/paddle/v2/fluid/tests/test_matmul_op.py
@@ -127,6 +127,7 @@ for dim_X in [1, 2, 3]:
                 })
 
 
+# Test case n-dim
 def generate_compatible_shapes(dim, transpose_X, transpose_Y):
     M = 2
     N = 4
@@ -135,14 +136,14 @@ def generate_compatible_shapes(dim, transpose_X, transpose_Y):
     shape_Y = [2 for _ in range(dim - 2)]
 
     if transpose_X:
-        shape_X = shape_X + [K, M]
+        shape_X += [K, M]
     else:
-        shape_X = shape_X + [M, K]
+        shape_X += [M, K]
 
     if transpose_Y:
-        shape_Y = shape_Y + [N, K]
+        shape_Y += [N, K]
     else:
-        shape_Y = shape_Y + [K, N]
+        shape_Y += [K, N]
 
     return shape_X, shape_Y