Natural Language Processing with Probabilistic Models
Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.
Natural Language Processing with Probabilistic Models
This course is part of Natural Language Processing Specialization
94,315 already enrolled
Ask Coursera
1,784 reviews
Recommended experience
1,784 reviews
Recommended experience
What you'll learn
Use dynamic programming, hidden Markov models, and word embeddings to implement autocorrect, autocomplete & identify part-of-speech tags for words.
Details to know
4 assignments
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 2 of the Natural Language Processing Specialization, you will:
a) Create a simple auto-correct algorithm using minimum edit distance and dynamic programming, b) Apply the Viterbi Algorithm for part-of-speech (POS) tagging, which is vital for computational linguistics, c) Write a better auto-complete algorithm using an N-gram language model, and d) Write your own Word2Vec model that uses a neural network to compute word embeddings using a continuous bag-of-words model. 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. Εukasz 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 about autocorrect, minimum edit distance, and dynamic programming, then build your own spellchecker to correct misspelled words!
What's included
11 videos11 readings1 assignment1 programming assignment2 ungraded labs
11 videosβ’Total 31 minutes
- Intro to Course 2β’2 minutes
- Week Introductionβ’1 minute
- Overviewβ’2 minutes
- Autocorrectβ’3 minutes
- Building the modelβ’4 minutes
- Building the model IIβ’3 minutes
- Minimum edit distanceβ’3 minutes
- Minimum edit distance algorithmβ’6 minutes
- Minimum edit distance algorithm IIβ’4 minutes
- Minimum edit distance algorithm IIIβ’3 minutes
- Week Conclusionβ’1 minute
11 readingsβ’Total 39 minutes
- Overviewβ’3 minutes
- Autocorrectβ’4 minutes
- Building the modelβ’3 minutes
- Building the model IIβ’4 minutes
- Minimum edit distanceβ’5 minutes
- Minimum edit distance algorithmβ’3 minutes
- Minimum edit distance algorithm IIβ’5 minutes
- Minimum edit distance IIIβ’4 minutes
- Join the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas!β’2 minutes
- Lecture Notes W1β’1 minute
- (Optional) Downloading your Notebook, Downloading your Workspace and Refreshing your Workspaceβ’5 minutes
1 assignmentβ’Total 30 minutes
- Auto-correct and Minimum Edit Distanceβ’30 minutes
1 programming assignmentβ’Total 180 minutes
- Autocorrectβ’180 minutes
2 ungraded labsβ’Total 120 minutes
- Lecture notebook: Building the vocabularyβ’60 minutes
- Lecture notebook: Candidates from editsβ’60 minutes
Learn about Markov chains and Hidden Markov models, then use them to create part-of-speech tags for a Wall Street Journal text corpus!
What's included
13 videos12 readings1 assignment1 programming assignment2 ungraded labs
13 videosβ’Total 43 minutes
- Week Introductionβ’1 minute
- Part of Speech Taggingβ’3 minutes
- Markov Chainsβ’4 minutes
- Markov Chains and POS Tagsβ’5 minutes
- Hidden Markov Modelsβ’4 minutes
- Calculating Probabilitiesβ’4 minutes
- Populating the Transition Matrixβ’5 minutes
- Populating the Emission Matrixβ’3 minutes
- The Viterbi Algorithmβ’5 minutes
- Viterbi: Initializationβ’2 minutes
- Viterbi: Forward Passβ’2 minutes
- Viterbi: Backward Passβ’5 minutes
- Week Conclusionβ’1 minute
12 readingsβ’Total 66 minutes
- Part of Speech Taggingβ’4 minutes
- Markov Chainsβ’3 minutes
- Markov Chains and POS Tagsβ’6 minutes
- Hidden Markov Modelsβ’6 minutes
- Calculating Probabilitiesβ’5 minutes
- Populating the Transition Matrixβ’6 minutes
- Populating the Emission Matrixβ’5 minutes
- The Viterbi Algorithmβ’5 minutes
- Viterbi Initializationβ’5 minutes
- Viterbi: Forward Passβ’10 minutes
- Viterbi: Backward Passβ’10 minutes
- Lecture Notes W2β’1 minute
1 assignmentβ’Total 30 minutes
- Part of Speech Taggingβ’30 minutes
1 programming assignmentβ’Total 180 minutes
- Part of Speech Tagging β’180 minutes
2 ungraded labsβ’Total 40 minutes
- Lecture Notebook - Working with text filesβ’20 minutes
- Lecture Notebook - Working with tags and Numpyβ’20 minutes
Learn about how N-gram language models work by calculating sequence probabilities, then build your own autocomplete language model using a text corpus from Twitter!
What's included
11 videos10 readings1 assignment1 programming assignment3 ungraded labs
11 videosβ’Total 53 minutes
- Week Introductionβ’1 minute
- N-Grams: Overviewβ’4 minutes
- N-grams and Probabilitiesβ’7 minutes
- Sequence Probabilitiesβ’5 minutes
- Starting and Ending Sentencesβ’9 minutes
- The N-gram Language Modelβ’7 minutes
- Language Model Evaluationβ’7 minutes
- Out of Vocabulary Wordsβ’5 minutes
- Smoothingβ’7 minutes
- Week Summaryβ’2 minutes
- Week Conclusionβ’1 minute
10 readingsβ’Total 70 minutes
- N-Grams Overviewβ’5 minutes
- N-grams and Probabilitiesβ’10 minutes
- Sequence Probabilitiesβ’6 minutes
- Starting and Ending Sentencesβ’6 minutes
- The N-gram Language Modelβ’10 minutes
- Language Model Evaluationβ’10 minutes
- Out of Vocabulary Wordsβ’10 minutes
- Smoothingβ’10 minutes
- Week Summaryβ’2 minutes
- Lecture Notes W3β’1 minute
1 assignmentβ’Total 30 minutes
- Autocompleteβ’30 minutes
1 programming assignmentβ’Total 180 minutes
- Autocompleteβ’180 minutes
3 ungraded labsβ’Total 180 minutes
- Lecture notebook: Corpus preprocessing for N-gramsβ’60 minutes
- Lecture notebook: Building the language modelβ’60 minutes
- Lecture notebook: Language model generalizationβ’60 minutes
Learn about how word embeddings carry the semantic meaning of words, which makes them much more powerful for NLP tasks, then build your own Continuous bag-of-words model to create word embeddings from Shakespeare text.
What's included
22 videos23 readings1 assignment1 programming assignment5 ungraded labs
22 videosβ’Total 73 minutes
- Week Introductionβ’1 minute
- Overviewβ’3 minutes
- Basic Word Representationsβ’4 minutes
- Word Embeddingsβ’4 minutes
- How to Create Word Embeddingsβ’4 minutes
- Word Embedding Methodsβ’3 minutes
- Continuous Bag-of-Words Modelβ’4 minutes
- Cleaning and Tokenizationβ’5 minutes
- Sliding Window of Words in Pythonβ’4 minutes
- Transforming Words into Vectorsβ’3 minutes
- Architecture of the CBOW Modelβ’3 minutes
- Architecture of the CBOW Model: Dimensionsβ’4 minutes
- Architecture of the CBOW Model: Dimensions 2β’3 minutes
- Architecture of the CBOW Model: Activation Functionsβ’5 minutes
- Training a CBOW Model: Cost Functionβ’5 minutes
- Training a CBOW Model: Forward Propagationβ’3 minutes
- Training a CBOW Model: Backpropagation and Gradient Descentβ’5 minutes
- Extracting Word Embedding Vectorsβ’3 minutes
- Evaluating Word Embeddings: Intrinsic Evaluationβ’3 minutes
- Evaluating Word Embeddings: Extrinsic Evaluationβ’3 minutes
- Conclusionβ’2 minutes
- Week Conclusionβ’1 minute
23 readingsβ’Total 90 minutes
- Overviewβ’0 minutes
- Basic Word Representationsβ’5 minutes
- Word Embeddingsβ’4 minutes
- How to Create Word Embeddings?β’4 minutes
- Word Embedding Methodsβ’4 minutes
- Continuous Bag of Words Modelβ’3 minutes
- Cleaning and Tokenizationβ’5 minutes
- Sliding Window of words in Pythonβ’10 minutes
- Transforming Words into Vectorsβ’2 minutes
- Architecture for the CBOW Modelβ’4 minutes
- Architecture of the CBOW Model: Dimensionsβ’4 minutes
- Architecture of the CBOW Model: Dimensions β’3 minutes
- Architecture of the CBOW Model: Activation Functionsβ’5 minutes
- Training a CBOW Model: Cost Functionβ’3 minutes
- Training a CBOW Model: Forward Propagationβ’3 minutes
- Training a CBOW Model: Backpropagation and Gradient Descentβ’4 minutes
- Extracting Word Embedding Vectorsβ’5 minutes
- Evaluating Word Embeddings: Intrinsic Evaluationβ’4 minutes
- Evaluating Word Embeddings: Extrinsic Evaluationβ’3 minutes
- Conclusionβ’2 minutes
- Lecture Notes W4β’1 minute
- [IMPORTANT] Reminder about end of access to Lab Notebooksβ’2 minutes
- Acknowledgmentsβ’10 minutes
1 assignmentβ’Total 30 minutes
- Word Embeddingsβ’30 minutes
1 programming assignmentβ’Total 180 minutes
- Word Embeddingsβ’180 minutes
5 ungraded labsβ’Total 180 minutes
- Lecture Notebook - Data Preparationβ’30 minutes
- Lecture Notebook - Intro to CBOW modelβ’30 minutes
- Lecture Notebook - Training the CBOW modelβ’40 minutes
- Lecture Notebook - Word Embeddingsβ’20 minutes
- Lecture notebook: Word embeddings step by stepβ’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
Course
- Status: Free Trial
Course
- Status: Free TrialD
DeepLearning.AI
Specialization
Why people choose Coursera for their career
Learner reviews
- 5 stars
79.55%
- 4 stars
14.90%
- 3 stars
3.41%
- 2 stars
0.84%
- 1 star
1.28%
Showing 3 of 1784
Reviewed on Jan 22, 2022
This class is one of the best on the subject. The prof is very knowledgeable and explains concepts very clearly. The code in the assignments and lectures is super clean and structured incredibly well.
Reviewed on Feb 12, 2021
Nicely broken into digestible chunks. Labs well done, not too easy, and too too frustrating. Material presented clearly and in (again) nice small steps.
Reviewed on Jul 13, 2020
I have a wonderful experience. Try not to look at the hints, resolve yourself, it is excellent course for getting the in depth knowledge of how the black boxes work. Happy learning.
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 canβt afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, youβll find a link to apply on the description page.
More questions
Financial aid available,