Explore
For Enterprise
Join for Free
Log In

Browse
Search
For Enterprise
Log In
Join for Free

Using APIs

Loading...

Natural Language Processing in TensorFlow

deeplearning.ai

4.6 (819 ratings) | 13K Students Enrolled

Course 3 of 4 in the TensorFlow in Practice Specialization

If you are a software developer who wants to build scalable AI-powered algorithms, you need to understand how to use the tools to build them. This Specialization will teach you best practices for using TensorFlow, a popular open-source framework for machine learning. In Course 3 of the deeplearning.ai TensorFlow Specialization, you will build natural language processing systems using TensorFlow. You will learn to process text, including tokenizing and representing sentences as vectors, so that they can be input to a neural network. You’ll also learn to apply RNNs, GRUs, and LSTMs in TensorFlow. Finally, you’ll get to train an LSTM on existing text to create original poetry! The Machine Learning course and Deep Learning Specialization from Andrew Ng teach the most important and foundational principles of Machine Learning and Deep Learning. This new deeplearning.ai TensorFlow Specialization teaches you how to use TensorFlow to implement those principles so that you can start building and applying scalable models to real-world problems. To develop a deeper understanding of how neural networks work, we recommend that you take the Deep Learning Specialization.

Skills You'll Learn

Natural Language Processing, Tokenization, Machine Learning, Tensorflow, RNNs

Reviews

4.6 (819 ratings)

5 stars
595 ratings
4 stars
166 ratings
3 stars
40 ratings
2 stars
12 ratings
1 star
6 ratings

SS

Aug 06, 2019

This course covers the overview of NLP without going into much mathematical detail. In short time span, many things can be learnt from this course, helpful for the beginners.

GI

Jun 22, 2019

Amazing course by Laurence Moroney. But only after finishing Sequence Models by Andrew NG, I was able to understand the concepts taught here.

From the lesson

Sentiment in text

The first step in understanding sentiment in text, and in particular when training a neural network to do so is the tokenization of that text. This is the process of converting the text into numeric values, with a number representing a word or a character. This week you'll learn about the Tokenizer and pad_sequences APIs in TensorFlow and how they can be used to prepare and encode text and sentences to get them ready for training neural networks!

Introduction1:16

Word based encodings2:14

Notebook for lesson 12:32

Text to sequence3:05

Looking more at the Tokenizer1:53

Notebook for lesson 24:18

Sarcasm, really?2:52

Working with the Tokenizer1:42

Notebook for lesson 33:14

Week 1 Wrap up0:21

Taught By

Laurence Moroney
AI Advocate

Transcript

Here's the code to encode the two sentences that we just spoke about. Let's unpack it line by line. Tensorflow and keras give us a number of ways to encode words, but the one I'm going to focus on is the tokenizer. This will handle the heavy lifting for us, generating the dictionary of word encodings and creating vectors out of the sentences. I'll put the sentences into an array. Note that I've already capitalized 'I' as it is at the beginning of the sentence. I then create an instance of the tokenizer. A passive parameter num wards to it. In this case, I'm using 100 which is way too big, as there are only five distinct words in this data. If you're creating a training set based on lots of text, you usually don't know how many unique distinct words there are in that text. So by setting this hyperparameter, what the tokenizer will do is take the top 100 words by volume and just encode those. It's a handy shortcut when dealing with lots of data, and worth experimenting with when you train with real data later in this course. Sometimes the impact of less words can be minimal and training accuracy, but huge in training time, but do use it carefully. The fit on texts method of the tokenizer then takes in the data and encodes it. The tokenizer provides a word index property which returns a dictionary containing key value pairs, where the key is the word, and the value is the token for that word, which you can inspect by simply printing it out. You can see the results here. Remember when we said that the word I was capitalized, note that it's lower-cased here. That's another thing that the tokenizer does for you. It strips punctuation out. This is really useful if you consider this case. Here, I've added another sentence, 'You love my dog!' but there's something very different about it. I've added an exclamation after the word 'dog!' Now, should this be treated as a different word than just dog? Well, of course not. So the results of the code that we saw earlier with this new corpus of data, will look like this. Notice that we still only have 'dog' as a key. That the exclamation didn't impact this, and of course, we have a new key for the word 'you' that was detected. So you've seen the beginnings of handling texts by creating word-based encodings of that text, with some very simple code intensive flow and keras. In the next video, we'll take a look at the code and see how it works.

Explore our Catalog

Join for free and get personalized recommendations, updates and offers.

Coursera provides universal access to the world’s best education, partnering with top universities and organizations to offer courses online.

© 2019 Coursera Inc. All rights reserved.

Get it on Google Play

Coursera
About
Leadership
Careers
Catalog
Certificates
MasterTrack™ Certificates
Degrees
For Enterprise
For Government

Community
Learners
Partners
Developers
Beta Testers
Translators

Connect
Blog
Facebook
LinkedIn
Twitter
Instagram
YouTube
Tech Blog

More
Terms
Privacy
Help
Accessibility
Press
Contact
Directory
Affiliates