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 cosine similarity and how it's used to compare embedding vectors</li>
	<li>Create a function that computes cosine similarities for a given word</li>
</ul>


<h2>A. Vector comparison</h2>

<div id="section1_l7" class="collapse show">
<p>In mathematics, the standard way for comparing vector similarity is through <i>cosine similarity</i>. Since word embeddings are just vectors of real numbers, we can use also cosine similarity to compare embeddings for different words.</p>
<p>For two vectors, <b>u</b> and <b>v</b>, the equation for cosine similarity is
</div>


$$\text{cos sim} = \frac{\mathbf{u}}{||\mathbf{u}||_2} \cdot \frac{\mathbf{v}}{||\mathbf{v}||_2}$$
where $\small ||v||_2$ represents the <a href="http://mathworld.wolfram.com/L2-Norm.html" target="_blank">L2-norm</a> of vector $v$, and $\cdot$ represents the dot product operation.</p>
We refer to the quantity $\frac{v}{||v||_2}$ as the L2-normalization of vector $\small v$.

<h2>B. Correlation</h2>

<p>The cosine similarity measures the <i>correlation</i> between two vectors, i.e. how closely related the two vectors are. The range of values for cosine similarity is [-1, 1]. A value of 1 means the vectors are perfectly identical, a value of -1 means the vectors are complete opposites, and a value of 0 means the vectors are <i>orthogonal</i> (i.e. completely uncorrelated).</p>


<h2>Chapter Goals:</h2>
<ul>
	<li>Learn about cosine similarity and how it's used to compare embedding vectors</li>
	<li>Create a function that computes cosine similarities for a given word</li>
</ul>


<h2>A. Vector comparison</h2>

<div id="section1_l7">
<p>In mathematics, the standard way for comparing vector similarity is through <i>cosine similarity</i>. Since word embeddings are just vectors of real numbers, we can use also cosine similarity to compare embeddings for different words.</p>
<p>For two vectors, <b>u</b> and <b>v</b>, the equation for cosine similarity is
</div>


Implement normalized cosine similarity to evaluate the embedding model.

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

Cosine Similarity

Chapter Goals:

A. Vector comparison

B. Correlation