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>Learn about the decoding process during training</li>
	<li>Create a <code>TrainingSampler</code> object to use for decoding</li>
</ul>


<h2>A. Decoding during training</h2>

<div id="section1_l6" class="collapse show">
<p>During training, we have access to both the input and output sequences of a training pair. This means that we can use the output sequence's ground truth tokens as input for the decoder.</p>
<p>We'll get into the specifics of TensorFlow decoding, i.e. using the decoder to generate model outputs, in later chapters. However, before we perform any decoding, we need to set up a <code>Sampler</code> object. For training, the <code>Sampler</code> object instance we use is the <code>TrainingSampler</code>.</p>
<p>Below, we create a <code>TrainingSampler</code> object for decoding during training.</p>


<h2>Chapter Goals:</h2>
<ul>
	<li>Learn about the decoding process during training</li>
	<li>Create a <code>TrainingSampler</code> object to use for decoding</li>
</ul>


<h2>A. Decoding during training</h2>

<div id="section1_l6">
<p>During training, we have access to both the input and output sequences of a training pair. This means that we can use the output sequence's ground truth tokens as input for the decoder.</p>
<p>We'll get into the specifics of TensorFlow decoding, i.e. using the decoder to generate model outputs, in later chapters. However, before we perform any decoding, we need to set up a <code>Sampler</code> object. For training, the <code>Sampler</code> object instance we use is the <code>TrainingSampler</code>.</p>
<p>Below, we create a <code>TrainingSampler</code> object for decoding during training.</p>


Create a Training Sampler object for training the decoder.

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

Training Sampler

Chapter Goals:

A. Decoding during training