Natural Language Processing with Classification and Vector Spaces
Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.
Natural Language Processing with Classification and Vector Spaces
This course is part of Natural Language Processing Specialization
221,150 already enrolled
4,638 reviews
Recommended experience
4,638 reviews
Recommended experience
What you'll learn
Use logistic regression, naïve Bayes, and word vectors to implement sentiment analysis, complete analogies & translate words.
Skills you'll gain
Tools you'll learn
Details to know
See how employees at top companies are mastering in-demand skills
Build your subject-matter 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
There are 4 modules in this course
In Course 1 of the Natural Language Processing Specialization, you will:
a) Perform sentiment analysis of tweets using logistic regression and then naïve Bayes, b) Use vector space models to discover relationships between words and use PCA to reduce the dimensionality of the vector space and visualize those relationships, and c) Write a simple English to French translation algorithm using pre-computed word embeddings and locality-sensitive hashing to relate words via approximate k-nearest neighbor search. By the end of this Specialization, you will have designed NLP applications that perform question-answering and sentiment analysis, created tools to translate languages and summarize text. This Specialization is designed and taught by two experts in NLP, machine learning, and deep learning. Younes Bensouda Mourri is an Instructor of AI at Stanford University who also helped build the Deep Learning Specialization. Łukasz Kaiser is a Staff Research Scientist at Google Brain and the co-author of Tensorflow, the Tensor2Tensor and Trax libraries, and the Transformer paper.
Learn to extract features from text into numerical vectors, then build a binary classifier for tweets using a logistic regression!
What's included
15 videos14 readings1 assignment1 programming assignment1 app item3 ungraded labs
15 videos•Total 85 minutes
- Welcome to the NLP Specialization•5 minutes
- Welcome to Course 1•2 minutes
- Week Introduction•1 minute
- Supervised ML & Sentiment Analysis•3 minutes
- Vocabulary & Feature Extraction•3 minutes
- Negative and Positive Frequencies•3 minutes
- Feature Extraction with Frequencies•3 minutes
- Preprocessing•3 minutes
- Putting it All Together•2 minutes
- Logistic Regression Overview•3 minutes
- Logistic Regression: Training•2 minutes
- Logistic Regression: Testing•5 minutes
- Logistic Regression: Cost Function•5 minutes
- Week Conclusion•1 minute
- Andrew Ng with Chris Manning•47 minutes
14 readings•Total 102 minutes
- Acknowledgement - Ken Church•10 minutes
- Supervised ML & Sentiment Analysis•2 minutes
- Vocabulary & Feature Extraction•2 minutes
- Feature Extraction with Frequencies•10 minutes
- Preprocessing•10 minutes
- Putting it all together•10 minutes
- Logistic Regression Overview•10 minutes
- Logistic Regression: Training•10 minutes
- Logistic Regression: Testing•10 minutes
- Optional Logistic Regression: Cost Function•10 minutes
- Optional Logistic Regression: Gradient•10 minutes
- Join the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas!•2 minutes
- Lecture Notes W1•1 minute
- (Optional) Downloading your Notebook, Downloading your Workspace and Refreshing your Workspace•5 minutes
1 assignment•Total 30 minutes
- Logistic Regression•30 minutes
1 programming assignment•Total 180 minutes
- Logistic Regression•180 minutes
1 app item•Total 1 minute
- Intake Survey•1 minute
3 ungraded labs•Total 180 minutes
- Natural Language preprocessing•60 minutes
- Visualizing word frequencies•60 minutes
- Visualizing tweets and Logistic Regression models•60 minutes
Learn the theory behind Bayes' rule for conditional probabilities, then apply it toward building a Naive Bayes tweet classifier of your own!
What's included
13 videos12 readings1 assignment1 programming assignment1 ungraded lab
13 videos•Total 44 minutes
- Week Introduction•0 minutes
- Probability and Bayes’ Rule•3 minutes
- Bayes’ Rule•4 minutes
- Naïve Bayes Introduction•6 minutes
- Laplacian Smoothing•3 minutes
- Log Likelihood, Part 1•6 minutes
- Log Likelihood, Part 2•2 minutes
- Training Naïve Bayes•4 minutes
- Testing Naïve Bayes•4 minutes
- Applications of Naïve Bayes•3 minutes
- Naïve Bayes Assumptions•3 minutes
- Error Analysis•4 minutes
- Week Conclusion•1 minute
12 readings•Total 111 minutes
- Probability and Bayes’ Rule•10 minutes
- Bayes' Rule•10 minutes
- Naive Bayes Introduction•10 minutes
- Laplacian Smoothing•10 minutes
- Log Likelihood, Part 1•10 minutes
- Log Likelihood Part 2•10 minutes
- Training naïve Bayes•10 minutes
- Testing naïve Bayes•10 minutes
- Applications of Naive Bayes•10 minutes
- Naïve Bayes Assumptions•10 minutes
- Error Analysis•10 minutes
- Lecture Notes W2•1 minute
1 assignment•Total 30 minutes
- Naive Bayes•30 minutes
1 programming assignment•Total 180 minutes
- Naive Bayes•180 minutes
1 ungraded lab•Total 60 minutes
- Visualizing likelihoods and confidence ellipses•60 minutes
Vector space models capture semantic meaning and relationships between words. You'll learn how to create word vectors that capture dependencies between words, then visualize their relationships in two dimensions using PCA.
What's included
10 videos10 readings1 assignment1 programming assignment3 ungraded labs
10 videos•Total 29 minutes
- Week Introduction•1 minute
- Vector Space Models•3 minutes
- Word by Word and Word by Doc. •5 minutes
- Euclidean Distance•3 minutes
- Cosine Similarity: Intuition•3 minutes
- Cosine Similarity•4 minutes
- Manipulating Words in Vector Spaces•3 minutes
- Visualization and PCA•3 minutes
- PCA Algorithm•4 minutes
- Week Conclusion•1 minute
10 readings•Total 91 minutes
- Vector Space Models•10 minutes
- Word by Word and Word by Doc.•10 minutes
- Euclidian Distance•10 minutes
- Cosine Similarity: Intuition•10 minutes
- Cosine Similarity•10 minutes
- Manipulating Words in Vector Spaces•10 minutes
- Visualization and PCA•10 minutes
- PCA algorithm•10 minutes
- The Rotation Matrix (Optional Reading)•10 minutes
- Lecture Notes W3•1 minute
1 assignment•Total 30 minutes
- Vector Space Models•30 minutes
1 programming assignment•Total 180 minutes
- Assignment: Vector Space Models•180 minutes
3 ungraded labs•Total 180 minutes
- Linear algebra in Python with Numpy•60 minutes
- Manipulating word embeddings •60 minutes
- Another explanation about PCA•60 minutes
Learn to transform word vectors and assign them to subsets using locality sensitive hashing, in order to perform machine translation and document search.
What's included
11 videos11 readings1 assignment1 programming assignment2 ungraded labs
11 videos•Total 68 minutes
- Week Introduction•1 minute
- Overview•2 minutes
- Transforming word vectors•7 minutes
- K-nearest neighbors•3 minutes
- Hash tables and hash functions•4 minutes
- Locality sensitive hashing•6 minutes
- Multiple Planes•4 minutes
- Approximate nearest neighbors•4 minutes
- Searching documents•2 minutes
- Week Conclusion•1 minute
- Andrew Ng with Kathleen McKeown•36 minutes
11 readings•Total 93 minutes
- Transforming word vectors•10 minutes
- K-nearest neighbors•10 minutes
- Hash tables and hash functions•10 minutes
- Locality sensitive hashing•10 minutes
- Multiple Planes•10 minutes
- Approximate nearest neighbors•10 minutes
- Searching documents•10 minutes
- Lecture Notes W4•1 minute
- [IMPORTANT] Reminder about end of access to Lab Notebooks•2 minutes
- Acknowledgements•10 minutes
- Bibliography•10 minutes
1 assignment•Total 30 minutes
- Hashing and Machine Translation•30 minutes
1 programming assignment•Total 180 minutes
- Word Translation•180 minutes
2 ungraded labs•Total 120 minutes
- Rotation matrices in R2•60 minutes
- Hash tables•60 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.
Instructors
Offered by
Explore more from Machine Learning
- Status: Free TrialD
DeepLearning.AI
Course
- Status: Free TrialD
DeepLearning.AI
Specialization
- Status: Free TrialD
DeepLearning.AI
Course
- Status: Free TrialD
DeepLearning.AI
Course
Why people choose Coursera for their career
Learner reviews
- 5 stars
73.95%
- 4 stars
18.96%
- 3 stars
4.48%
- 2 stars
1.27%
- 1 star
1.31%
Showing 3 of 4638
Reviewed on Apr 20, 2021
The material was a little shallow in places, and there are some long standing issues with assignments and quizzes that remain unresolved. Other than that, it was an interesting course.
Reviewed on Oct 15, 2022
This course is excellent and is well-organized. I would definitely recommend it to others. The instructor explains the topic in a crystal clear way. I learned a lot and had a great time. Thanks!
Reviewed on Aug 1, 2020
Video lectures are short and concise. The basic ideas are well presented. Some references for the details of vector subspaces and spanning vectors would have filled out the mathematical framework.
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 Specialization, 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.
Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.
More questions
Financial aid available,