Fix typo in IMDB tutorial

PiperOrigin-RevId: 268329711

Author: arjung

g3doc/tutorials/graph_keras_lstm_imdb.ipynb

@@ -43,17 +43,17 @@
  "source": [
  "# Graph regularization for sentiment classification using synthesized graphs\n",
  "\n",
- "<table class=\"tfo-notebook-buttons\" align=\"left\">\n",
- " <td>\n",
- " <a target=\"_blank\" href=\"https://www.tensorflow.org/neural_structured_learning/tutorials/graph_keras_lstm_imdb\"><img src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" />View on TensorFlow.org</a>\n",
- " </td>\n",
- " <td>\n",
- " <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/neural-structured-learning/blob/master/g3doc/tutorials/graph_keras_lstm_imdb.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
- " </td>\n",
- " <td>\n",
- " <a target=\"_blank\" href=\"https://github.com/tensorflow/neural-structured-learning/blob/master/g3doc/tutorials/graph_keras_lstm_imdb.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
- " </td>\n",
- "</table>"
+ "\u003ctable class=\"tfo-notebook-buttons\" align=\"left\"\u003e\n",
+ " \u003ctd\u003e\n",
+ " \u003ca target=\"_blank\" href=\"https://www.tensorflow.org/neural_structured_learning/tutorials/graph_keras_lstm_imdb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" /\u003eView on TensorFlow.org\u003c/a\u003e\n",
+ " \u003c/td\u003e\n",
+ " \u003ctd\u003e\n",
+ " \u003ca target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/neural-structured-learning/blob/master/g3doc/tutorials/graph_keras_lstm_imdb.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" /\u003eRun in Google Colab\u003c/a\u003e\n",
+ " \u003c/td\u003e\n",
+ " \u003ctd\u003e\n",
+ " \u003ca target=\"_blank\" href=\"https://github.com/tensorflow/neural-structured-learning/blob/master/g3doc/tutorials/graph_keras_lstm_imdb.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" /\u003eView source on GitHub\u003c/a\u003e\n",
+ " \u003c/td\u003e\n",
+ "\u003c/table\u003e"
  ]
  },
  {
@@ -344,10 +344,10 @@
  "\n",
  " # The first indices are reserved\n",
  " word_index = {k: (v + 3) for k, v in word_index.items()}\n",
- " word_index['<PAD>'] = 0\n",
- " word_index['<START>'] = 1\n",
- " word_index['<UNK>'] = 2 # unknown\n",
- " word_index['<UNUSED>'] = 3\n",
+ " word_index['\u003cPAD\u003e'] = 0\n",
+ " word_index['\u003cSTART\u003e'] = 1\n",
+ " word_index['\u003cUNK\u003e'] = 2 # unknown\n",
+ " word_index['\u003cUNUSED\u003e'] = 3\n",
  " return dict((value, key) for (key, value) in word_index.items())\n",
  "\n",
  "reverse_word_index = build_reverse_word_index()\n",
@@ -569,9 +569,9 @@
  "source": [
  "## Sample features\n",
  "\n",
- "We create sample features for our problem in the `tf.train.Example`s format and\n",
- "persist them in the `TFRecord` format. Each sample will include the following\n",
- "three features:\n",
+ "We create sample features for our problem using the `tf.train.Example` format\n",
+ "and persist them in the `TFRecord` format. Each sample will include the\n",
+ "following three features:\n",
  "\n",
  "1. **id**: The node ID of the sample.\n",
  "2. **words**: An int64 list containing word IDs.\n",
@@ -774,11 +774,11 @@
  "source": [
  "### Prepare the data\n",
  "\n",
- "The reviews\u2014the arrays of integers\u2014must be converted to tensors before being fed\n",
+ "The reviews—the arrays of integers—must be converted to tensors before being fed\n",
  "into the neural network. This conversion can be done a couple of ways:\n",
  "\n",
  "* Convert the arrays into vectors of `0`s and `1`s indicating word occurrence,\n",
- " similar to a one-hot encoding. For example, the sequence `[3, 5]` would become a `10000`-dimensional vector that is all zeros except for indices `3` and `5`, which are ones. Then, make this the first layer in our network\u2014a `Dense` layer\u2014that can handle floating point vector data. This approach is memory intensive, though, requiring a `num_words * num_reviews` size matrix.\n",
+ " similar to a one-hot encoding. For example, the sequence `[3, 5]` would become a `10000`-dimensional vector that is all zeros except for indices `3` and `5`, which are ones. Then, make this the first layer in our network—a `Dense` layer—that can handle floating point vector data. This approach is memory intensive, though, requiring a `num_words * num_reviews` size matrix.\n",
  "\n",
  "* Alternatively, we can pad the arrays so they all have the same length, then\n",
  " create an integer tensor of shape `max_length * num_reviews`. We can use an\n",
@@ -885,7 +885,7 @@
  "source": [
  "### Build the model\n",
  "\n",
- "A neural network is created by stacking layers\u2014this requires two main architectural decisions:\n",
+ "A neural network is created by stacking layers—this requires two main architectural decisions:\n",
  "\n",
  "* How many layers to use in the model?\n",
  "* How many *hidden units* to use for each layer?\n",
@@ -982,7 +982,7 @@
  "If a model has more hidden units (a higher-dimensional representation space),\n",
  "and/or more layers, then the network can learn more complex representations.\n",
  "However, it makes the network more computationally expensive and may lead to\n",
- "learning unwanted patterns\u2014patterns that improve performance on training data\n",
+ "learning unwanted patterns—patterns that improve performance on training data\n",
  "but not on the test data. This is called *overfitting*."
  ]
  },
@@ -1204,7 +1204,7 @@
  "source": [
  "Notice the training loss *decreases* with each epoch and the training accuracy\n",
  "*increases* with each epoch. This is expected when using a gradient descent\n",
- "optimization\u2014it should minimize the desired quantity on every iteration."
+ "optimization—it should minimize the desired quantity on every iteration."
  ]
  },
  {