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>Extract the word predictions for the final time step of each sequence</li>
</ul>


<h2>A. Gather functions</h2>

<div id="section1_l9" class="collapse show">
<p>When generating word predictions for a batch of sequences, we only want to retrieve the word IDs for each sequence's final time step. If this were regular Python (or NumPy), we could do this through simple list indexing or slicing. However, in TensorFlow we need to use <i>gather</i> functions to retrieve data at specific locations in the tensor.</p>
<p>There are two main gather functions: <code><a href="https://www.tensorflow.org/api_docs/python/tf/gather" target="_blank">tf.gather</code></a></code> and <code><a href="https://www.tensorflow.org/api_docs/python/tf/gather_nd" target="_blank">tf.gather_nd</a></code>. Both take in the same two required arguments:
<ul>
	<li><b>params:</b> The tensor that we wish to retrieve data from.</li>
	<li><b>indices:</b> The locations in the tensor that we will index into.</li>
</ul>
</p>
<p>The <code>tf.gather</code> function can be used to retrieve specific slices from a tensor, based on what the <code>axis</code> keyword argument is set to (default is <code>0</code>).</p>
<p>Below are example usages of <code>tf.gather</code>. Note that the values in the <code>indices</code> argument must by valid indices for the specified <code>axis</code>.</p>

<h2>Chapter Goals:</h2>
<ul>
	<li>Extract the word predictions for the final time step of each sequence</li>
</ul>


<h2>A. Gather functions</h2>

<div id="section1_l9">
<p>When generating word predictions for a batch of sequences, we only want to retrieve the word IDs for each sequence's final time step. If this were regular Python (or NumPy), we could do this through simple list indexing or slicing. However, in TensorFlow we need to use <i>gather</i> functions to retrieve data at specific locations in the tensor.</p>
<p>There are two main gather functions: <code><a href="https://www.tensorflow.org/api_docs/python/tf/gather" target="_blank">tf.gather</code></a></code> and <code><a href="https://www.tensorflow.org/api_docs/python/tf/gather_nd" target="_blank">tf.gather_nd</a></code>. Both take in the same two required arguments:
<ul>
	<li><b>params:</b> The tensor that we wish to retrieve data from.</li>
	<li><b>indices:</b> The locations in the tensor that we will index into.</li>
</ul>
</p>
<p>The <code>tf.gather</code> function can be used to retrieve specific slices from a tensor, based on what the <code>axis</code> keyword argument is set to (default is <code>0</code>).</p>
<p>Below are example usages of <code>tf.gather</code>. Note that the values in the <code>indices</code> argument must by valid indices for the specified <code>axis</code>.</p>

Use tensor indexing to retrieve the model's final word prediction.

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

Tensor Indexing

Chapter Goals:

A. Gather functions