Natural Language Processing in TensorFlow
Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.
Natural Language Processing in TensorFlow
This course is part of DeepLearning.AI TensorFlow Developer Professional Certificate
Instructor: Laurence Moroney
153,813 already enrolled
Ask Coursera
6,537 reviews
Recommended experience
6,537 reviews
Recommended experience
What you'll learn
Build natural language processing systems using TensorFlow
Process text, including tokenization and representing sentences as vectors
Apply RNNs, GRUs, and LSTMs in TensorFlow
Train LSTMs on existing text to create original poetry and more
Skills you'll gain
Tools you'll learn
Details to know
See how employees at top companies are mastering in-demand skills
Build your Machine Learning expertise
- Learn new concepts from industry experts
- Gain a foundational understanding of a subject or tool
- Develop job-relevant skills with hands-on projects
- Earn a shareable career certificate from DeepLearning.AI
There are 4 modules in this course
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 Developer 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 Developer 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.
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!
What's included
13 videos7 readings1 assignment1 programming assignment3 ungraded labs
13 videos•Total 26 minutes
- Introduction: A conversation with Andrew Ng•1 minute
- Introduction•1 minute
- Word based encodings•2 minutes
- Using APIs•2 minutes
- Notebook for lesson 1•2 minutes
- Text to sequence•3 minutes
- Padding•3 minutes
- Out-of-Vocabulary Words•2 minutes
- Notebook for lesson 2•4 minutes
- Sarcasm, really?•3 minutes
- Preprocessing the Sarcasm dataset•1 minute
- Notebook for lesson 3•2 minutes
- Week 1 Wrap up•0 minutes
7 readings•Total 21 minutes
- Welcome to the course!•1 minute
- About the notebooks in this course•5 minutes
- News headlines dataset for sarcasm detection•2 minutes
- Join the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas!•2 minutes
- Lecture Notes Week 1•1 minute
- Assignment Troubleshooting Tips•5 minutes
- (Optional) Downloading your Notebook and Refreshing your Workspace•5 minutes
1 assignment•Total 30 minutes
- Week 1 Quiz•30 minutes
1 programming assignment•Total 180 minutes
- Explore the BBC news archive•180 minutes
3 ungraded labs•Total 60 minutes
- Check out the code! (Lab 1)•20 minutes
- Check out the code! (Lab 2)•20 minutes
- Check out the code! (Lab 3)•20 minutes
Last week you saw how to use the Tokenizer to prepare your text to be used by a neural network by converting words into numeric tokens, and sequencing sentences from these tokens. This week you'll learn about Embeddings, where these tokens are mapped as vectors in a high dimension space. With Embeddings and labelled examples, these vectors can then be tuned so that words with similar meaning will have a similar direction in the vector space. This will begin the process of training a neural network to understand sentiment in text -- and you'll begin by looking at movie reviews, training a neural network on texts that are labelled 'positive' or 'negative' and determining which words in a sentence drive those meanings.
What's included
12 videos4 readings1 assignment1 programming assignment3 ungraded labs
12 videos•Total 27 minutes
- A conversation with Andrew Ng•2 minutes
- Introduction•2 minutes
- The IMDB dataset•1 minute
- Looking into the details•4 minutes
- How can we use vectors?•2 minutes
- More into the details•2 minutes
- Notebook for lesson 1•7 minutes
- Remember the sarcasm dataset?•1 minute
- Building a classifier for the sarcasm dataset•2 minutes
- Let’s talk about the loss•1 minute
- Subword tokenization•1 minute
- Diving into the code•3 minutes
4 readings•Total 17 minutes
- IMDB reviews dataset•1 minute
- Subword tokenization•10 minutes
- Week 2 Wrap up•1 minute
- Lecture Notes Week 2•5 minutes
1 assignment•Total 30 minutes
- Week 2 Quiz•30 minutes
1 programming assignment•Total 180 minutes
- Diving deeper into the BBC News archive•180 minutes
3 ungraded labs•Total 90 minutes
- Check out the code! (Lab 1)•30 minutes
- Check out the code! (Lab 2)•30 minutes
- Check out the code! (Lab 3)•30 minutes
In the last couple of weeks you looked first at Tokenizing words to get numeric values from them, and then using Embeddings to group words of similar meaning depending on how they were labelled. This gave you a good, but rough, sentiment analysis -- words such as 'fun' and 'entertaining' might show up in a positive movie review, and 'boring' and 'dull' might show up in a negative one. But sentiment can also be determined by the sequence in which words appear. For example, you could have 'not fun', which of course is the opposite of 'fun'. This week you'll start digging into a variety of model formats that are used in training models to understand context in sequence!
What's included
10 videos4 readings1 assignment1 programming assignment6 ungraded labs
10 videos•Total 16 minutes
- A conversation with Andrew Ng•2 minutes
- Introduction•3 minutes
- LSTMs•2 minutes
- Implementing LSTMs in code•1 minute
- Accuracy and loss•2 minutes
- A word from Laurence•1 minute
- Looking into the code•2 minutes
- Using a convolutional network•2 minutes
- Going back to the IMDB dataset•1 minute
- Tips from Laurence•1 minute
4 readings•Total 22 minutes
- Link to Andrew's sequence modeling course•10 minutes
- More info on LSTMs•10 minutes
- Week 3 Wrap up•1 minute
- Lecture Notes Week 3•1 minute
1 assignment
- Week 3 Quiz•0 minutes
1 programming assignment•Total 180 minutes
- Exploring overfitting in NLP•180 minutes
6 ungraded labs•Total 180 minutes
- Check out the code! (Lab 1)•30 minutes
- Check out the code! (Lab 2)•30 minutes
- Check out the code! (Lab 3)•30 minutes
- Check out the code! (Lab 4)•30 minutes
- Exploring a Bidirectional LSTM (Lab 5)•30 minutes
- Exploring a Convolutional Network (Lab 6)•30 minutes
Taking everything that you've learned in training a neural network based on NLP, we thought it might be a bit of fun to turn the tables away from classification and use your knowledge for prediction. Given a body of words, you could conceivably predict the word most likely to follow a given word or phrase, and once you've done that, to do it again, and again. With that in mind, this week you'll build a poetry generator. It's trained with the lyrics from traditional Irish songs, and can be used to produce beautiful-sounding verse of it's own!
What's included
14 videos5 readings1 assignment1 programming assignment3 ungraded labs
14 videos•Total 23 minutes
- A conversation with Andrew Ng•1 minute
- Introduction•1 minute
- Looking into the code•1 minute
- Preparing the training data•2 minutes
- More on the training data•2 minutes
- Finding what the next word should be•2 minutes
- Example•1 minute
- Predicting a word•2 minutes
- Notebook for lesson 1•5 minutes
- Poetry!•1 minute
- Looking into the code•1 minute
- Laurence the poet!•1 minute
- Your next task•1 minute
- A conversation with Andrew Ng•1 minute
5 readings•Total 15 minutes
- Link to the dataset•1 minute
- Lecture Notes Week 4•1 minute
- [IMPORTANT] Reminder about end of access to Lab Notebooks•2 minutes
- Wrap up•10 minutes
- Acknowledgments•1 minute
1 assignment•Total 30 minutes
- Week 4 Quiz•30 minutes
1 programming assignment•Total 180 minutes
- Predicting the next word•180 minutes
3 ungraded labs•Total 80 minutes
- Check out the code! (Lab 1)•30 minutes
- Check out the code! (Lab 2)•30 minutes
- (optional) Generating text using a character-based RNN•20 minutes
Earn a career certificate
Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.
Instructor
Offered by
Explore more from Machine Learning
- Status: Free Trial
- Status: Free TrialD
DeepLearning.AI
Course
- Status: Free Trial
- Status: Free TrialG
Google Cloud
Course
Why people choose Coursera for their career
Learner reviews
- 5 stars
72.98%
- 4 stars
18.84%
- 3 stars
5.56%
- 2 stars
1.56%
- 1 star
1.04%
Showing 3 of 6537
Reviewed on Jul 21, 2020
Great course for anyone interested in NLP! This course focuses on practical learning instead of overburdening students with theory. Would recommend this to every NLP beginner/enthusiast out there!!
Reviewed on Feb 28, 2020
Excellent courseGave me a brief idea with practical experience about how to process strings for machine learning.I would like to thank Laurence Sir and a Special thanks to Andrew Sir
Reviewed on Dec 29, 2019
This is good course for those who are want to practice in natural language processing in Tensor Flow and also learned sentiment analysis it is having wonderful stuff for beginners
Frequently asked questions
To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
When you enroll in the course, you get access to all of the courses in the Certificate, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.
More questions
Financial aid available,