diff --git a/chapter_computer-vision/semantic-segmentation-and-dataset.md b/chapter_computer-vision/semantic-segmentation-and-dataset.md
index a0c7611752..a0e436bc5c 100644
--- a/chapter_computer-vision/semantic-segmentation-and-dataset.md
+++ b/chapter_computer-vision/semantic-segmentation-and-dataset.md
@@ -39,7 +39,7 @@ distinguish them from semantic segmentation as follows.
 
 ## The Pascal VOC2012 Semantic Segmentation Dataset
 
-[**On of the most important semantic segmentation dataset
+[**One of the most important semantic segmentation dataset
 is [Pascal VOC2012](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/).**]
 In the following,
 we will take a look at this dataset.
diff --git a/chapter_hyperparameter-optimization/hyperopt-api.md b/chapter_hyperparameter-optimization/hyperopt-api.md
index 8135aa94e4..2a91c3aefd 100644
--- a/chapter_hyperparameter-optimization/hyperopt-api.md
+++ b/chapter_hyperparameter-optimization/hyperopt-api.md
@@ -178,7 +178,7 @@ def bookkeeping(self, config: dict, error: float, runtime: float):
 
 We now use our new implementation of random search to optimize the
 *batch size* and *learning rate* of the `LeNet` convolutional neural network
-from :numref:`sec_lenet`. We being by defining the objective function, which
+from :numref:`sec_lenet`. We begin by defining the objective function, which
 will once more be validation error.
 
 ```{.python .input  n=9}