Gain insights into processing text data, creating word embeddings, and using LSTMs for semantic analysis and machine translation. Explore industry-relevant NLP techniques with Python and TensorFlow.

nlp_docker.tar.gz

mnist-fashion

In this course you'll learn techniques for processing text data, creating word embeddings, and using long short-term memory networks (LSTM) for tasks such as semantic analysis and machine translation. After completing this course, you will be able to solve the important day-to-day NLP problems faced in industry, which is incredibly useful given the prevalence of text data.

The code for this course is built around the TensorFlow framework, one of the premier frameworks for industry machine learning, and the Python pandas library for data analysis. Knowledge of Python and TensorFlow are prerequisites. 

This course was created by AdaptiLab, a company specializing in evaluating, sourcing, and upskilling enterprise machine learning talent. It is built in collaboration with industry machine learning experts from Google, Microsoft, Amazon, and Apple.

Natural Language Processing with Machine Learning

<h2 class="section-title">Chapter Goals:</h2>
<ul>
	<li>Compute the output of your LSTM model</li>
</ul>


<h2>A. TensorFlow implementation</h2>

<div id="section1_l6" class="collapse show">
<p>In TensorFlow, the way we create and run an RNN is with the function <code><a href="https://www.tensorflow.org/api_docs/python/tf/keras/layers/RNN" target="_blank">tf.keras.layers.RNN</a></code>. The function takes in two required arguments. The first is the cell object that is used to create the RNN (e.g. an <code>LSTMCell</code>, <code>StackedRNNCells</code>, etc.). The second is the batch of input sequences, which are usually first converted to word embedding sequences.</p>
<p>Of the keyword arguments for the function, it is required that either <code>initial_state</code> or <code>dtype</code> is set. The <code>initial_state</code> argument specifies the starting state for the input cell object. We'll use this argument in later parts of this section.</p>
<p>The <code>dtype</code> argument specifies the type of both the initial cell state and RNN output. Most of the time, we can just set this argument to <code>tf.float32</code>, since the RNN outputs are normally floating point numbers.</p>
<p>Below is an example demonstrating how to use <code>tf.keras.layers.RNN</code>. Note that the input sequences have maximum length 10 and embedding size 12.</p>

<h2>Chapter Goals:</h2>
<ul>
	<li>Compute the output of your LSTM model</li>
</ul>


<h2>A. TensorFlow implementation</h2>

<div id="section1_l6">
<p>In TensorFlow, the way we create and run an RNN is with the function <code><a href="https://www.tensorflow.org/api_docs/python/tf/keras/layers/RNN" target="_blank">tf.keras.layers.RNN</a></code>. The function takes in two required arguments. The first is the cell object that is used to create the RNN (e.g. an <code>LSTMCell</code>, <code>StackedRNNCells</code>, etc.). The second is the batch of input sequences, which are usually first converted to word embedding sequences.</p>
<p>Of the keyword arguments for the function, it is required that either <code>initial_state</code> or <code>dtype</code> is set. The <code>initial_state</code> argument specifies the starting state for the input cell object. We'll use this argument in later parts of this section.</p>
<p>The <code>dtype</code> argument specifies the type of both the initial cell state and RNN output. Most of the time, we can just set this argument to <code>tf.float32</code>, since the RNN outputs are normally floating point numbers.</p>
<p>Below is an example demonstrating how to use <code>tf.keras.layers.RNN</code>. Note that the input sequences have maximum length 10 and embedding size 12.</p>

Run an LSTM model on input sequences and retrieve the output.

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

LSTM Output

Chapter Goals:

A. TensorFlow implementation