Fixes typos in the the 1st graph Keras tutorial.

PiperOrigin-RevId: 293631855

Author: Neural-Link Team

g3doc/tutorials/graph_keras_mlp_cora.ipynb

@@ -320,7 +320,7 @@
       "source": [
         "## Hyperparameters\n",
         "\n",
-        "We will use an instance of `HParams` to inclue various hyperparameters and\n",
+        "We will use an instance of `HParams` to include various hyperparameters and\n",
         "constants used for training and evaluation. We briefly describe each of them\n",
         "below:\n",
         "\n",
@@ -402,7 +402,7 @@
         "\n",
         "In the input layer of our model, we will extract not just the 'words' and the\n",
         "'label' features from each sample, but also corresponding neighbor features\n",
-        "based on the `hparams.num_neighbors`. Instances with fewer neighbors than\n",
+        "based on the `hparams.num_neighbors` value. Instances with fewer neighbors than\n",
         "`hparams.num_neighbors` will be assigned dummy values for those non-existent\n",
         "neighbor features."
       ]
@@ -425,7 +425,7 @@
         "\n",
         "  Returns:\n",
         "    A pair whose first value is a dictionary containing relevant features\n",
-        "    and whose second value contains the ground truth labels.\n",
+        "    and whose second value contains the ground truth label.\n",
         "  \"\"\"\n",
         "  # The 'words' feature is a multi-hot, bag-of-words representation of the\n",
         "  # original raw text. A default value is required for examples that don't\n",
@@ -459,9 +459,8 @@
         "        [1], tf.float32, default_value=tf.constant([0.0]))\n",
         "\n",
         "  features = tf.io.parse_single_example(example_proto, feature_spec)\n",
-        "\n",
-        "  labels = features.pop('label')\n",
-        "  return features, labels\n",
+        "  label = features.pop('label')\n",
+        "  return features, label\n",
         "\n",
         "\n",
         "def make_dataset(file_path, training=False):\n",