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 how to improve the performance of the BiLSTM classifier</li>
</ul>


<h2>A. Model performance</h2>

<div id="section2_l7" class="collapse show">
<p>The current iteration of the model will perform well on relatively simple datasets and can even perform adequately on larger datasets. However, there are still improvements that can be made to the model.</p>
<p>An easy way to improve the model would be to use more LSTM layers or hidden LSTM units. Our model only used a single LSTM layer with 512 hidden units, so adding more LSTM layers may benefit the model's performance. However, similar to adding hidden layers to a feed-forward neural network, it is important to make sure that additional LSTM layers don't lead to the model overfitting the training dataset.</p>
</div>


<h2>B. Movie review sentiment analysis model</h2>

The code below runs a text classification model which has been implemented in the backend. The model classifies a given movie review as either positive or negative.

Paste in your own movie review to the text prompt and see whether the model thinks it's positive or negative!

<h2>Chapter Goals:</h2>
<ul>
	<li>Learn how to improve the performance of the BiLSTM classifier</li>
</ul>


<h2>A. Model performance</h2>

<div id="section2_l7">
<p>The current iteration of the model will perform well on relatively simple datasets and can even perform adequately on larger datasets. However, there are still improvements that can be made to the model.</p>
<p>An easy way to improve the model would be to use more LSTM layers or hidden LSTM units. Our model only used a single LSTM layer with 512 hidden units, so adding more LSTM layers may benefit the model's performance. However, similar to adding hidden layers to a feed-forward neural network, it is important to make sure that additional LSTM layers don't lead to the model overfitting the training dataset.</p>
</div>


Tips and advice on how to improve the BiLSTM model performance.

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

Improving the Model

Chapter Goals:

A. Model performance

B. Movie review sentiment analysis model