Natural Language Processing Specialization

Natural Language Processing with Classification and Vector Spaces

Week 1 : Sentiment Analysis with Logistic Regression

Lecture: Logistic Regression

• Video : Welcome to the NLP Specialization
• Video : Welcome to course 1
• Reading : Acknowledgment - Ken Church
• Video : Week Introduction
• Video : Supervised ML & Sentiment Analysis
• Reading : Supervised ML & Sentiment Analysis
• Video : Vocabulary & Feature Extraction
• Reading : Vocabulary & Feature Extraction
• Video : Negative and Positive Frequencies
• Video : Feature Extraction with Frequencies
• Reading : Feature Extraction with Frequencies
• Video : Preprocessing
• Reading : Preprocessing
• Lab : Natural Language preprocessing
• Video : Putting it All Together
• Reading : Putting it all together
• Lab : Visualizing word frequencies
• Video : Logistic Regression Overview
• Reading : Logistic Regression Overview
• Video : Logistic Regression: Training
• Reading : Logistic Regression: Training
• Lab : Visualizing tweets and Logistic Regression models
• Video : Logistic Regression: Testing
• Reading : Logistic Regression: Testing
• Video : Logistic Regression: Cost Function
• Reading : Optional Logistic Regression: Cost Function
• Video : Week Conclusion
• Reading : Optional Logistic Regression: Gradient
• Ungraded App Item : Intake Survey)
• Have questions, issues or ideas? Join our Community!

Lecture Notes (Optional)

• Reading : Lecture Notes W1

Practice Quiz

• Practice Quiz : Logistic Regression

Assignment: Sentiment Analysis with Logistic Regression

• Reading : (Optional) Downloading your Notebook, Downloading your Workspace and Refreshing your Workspace
• Programming Assignment : Logistic Regression

Heroes of NLP: Chris Manning (Optional)

• Video : Andrew Ng with Chris Manning

Week 2 : Sentiment Analysis with Naïve Bayes

Lecture: Naive Bayes

• Video : Week Introduction
• Video : Probability and Bayes’ Rule
• Reading : Probability and Bayes’ Rule
• Video : Bayes’ Rule
• Reading : Bayes' Rule
• Video : Naïve Bayes Introduction
• Reading : Naive Bayes Introduction
• Video : Laplacian Smoothing
• Reading : Laplacian Smoothing
• Video : Log Likelihood, Part 1
• Reading : Log Likelihood, Part 1
• Video : Log Likelihood, Part 2
• Reading : Log Likelihood Part 2
• Video : Training Naïve Bayes
• Reading : Training naïve Bayes
• Lab : Visualizing likelihoods and confidence ellipses
• Video : Testing Naïve Bayes
• Reading : Testing naïve Bayes
• Video : Applications of Naïve Bayes
• Reading : Applications of Naive Bayes
• Video : Naïve Bayes Assumptions
• Reading : Naïve Bayes Assumptions
• Video : Error Analysis
• Reading : Error Analysis
• Video : Week Conclusion

Lecture Notes (Optional)

• Lecture Notes W2

Practice Quiz

• Naive Bayes

Assignment: Naive Bayes

• Programming Assignment : Naive Bayes

Week 3 : Vector Space Models

Lecture: Vector Space Models

• Video : Week Introduction
• Video : Vector Space Models
• Reading : Vector Space Models
• Video : Word by Word and Word by Doc.
• Reading : Word by Word and Word by Doc.
• Lab : Linear algebra in Python with Numpy
• Video : Euclidean Distance
• Reading : Euclidian Distance
• Video : Cosine Similarity: Intuition
• Reading : Cosine Similarity: Intuition
• Video : Cosine Similarity
• Reading : Cosine Similarity
• Video : Manipulating Words in Vector Spaces
• Reading : Manipulating Words in Vector Spaces
• Lab : Manipulating word embeddings
• Video : Visualization and PCA
• Reading : Visualization and PCA
• Video : PCA Algorithm
• Reading : PCA algorithm
• Lab : Another explanation about PCA
• Reading : The Rotation Matrix (Optional Reading)
• Video : Week Conclusion

Lecture Notes (Optional)

• Reading : Lecture Notes W3

Practice Quiz

• Practice Quiz : Vector Space Models

Assignment: Vector Space Models

• Programming Assignment : Assignment: Vector Space Models

Week 4 : Machine Translation and Document Search

Lecture: Machine Translation

• Video : Week Introduction
• Video : Overview
• Video : Transforming word vectors
• Reading : Transforming word vectors
• Lab : Rotation matrices in R2
• Video : K-nearest neighbors
• Reading : K-nearest neighbors
• Video : Hash tables and hash functions
• Reading : Hash tables and hash functions
• Video : Locality sensitive hashing
• Reading : Locality sensitive hashing
• Video : Multiple Planes
• Reading : Multiple Planes
• Lab : Hash tables
• Video : Approximate nearest neighbors
• Reading : Approximate nearest neighbors
• Video : Searching documents
• Reading : Searching documents
• Video : Week Conclusion

Lecture Notes (Optional)

• Reading : Lecture Notes W4

Practice Quiz

• Practice Quiz : Hashing and Machine Translation

Assignment: Machine Translation

• Programming Assignment : Word Translation

Acknowledgments and Bibliography

• Reading : Acknowledgements
• Reading : Bibliography

Heroes of NLP: Kathleen McKeown

• Video : Andrew Ng with Kathleen McKeown

Natural Language Processing with Probabilistic Models

Week 1

Lecture: Autocorrect and Minimum Edit Distance

• Video : Intro to Course 2
• Video : Week Introduction
• Video : Overview
• Reading : Overview
• Video : Autocorrect
• Reading : Autocorrect
• Video : Building the model
• Reading : Building the model
• Lab : Lecture notebook: Building the vocabulary
• Video : Building the model II
• Reading : Building the model II
• Lab : Lecture notebook: Candidates from edits
• Video : Minimum edit distance
• Reading : Minimum edit distance
• Video : Minimum edit distance algorithm
• Reading : Minimum edit distance algorithm
• Video : Minimum edit distance algorithm II
• Reading : Minimum edit distance algorithm II
• Video : Minimum edit distance algorithm III
• Reading : Minimum edit distance III
• Video : Week Conclusion
• Ungraded App Item : [IMPORTANT] Have questions, issues or ideas? Join our Community!

Lecture Notes (Optional)

• Reading : Lecture Notes W1

Quiz: Auto-correct and Minimum Edit Distance

• Practice Quiz : Auto-correct and Minimum Edit Distance

Assignment: Autocorrect

• Reading : (Optional) Downloading your Notebook, Downloading your Workspace and Refreshing your Workspace
• Programming Assignment : Autocorrect

Week 2

Lecture: Part of Speech Tagging

• Video : Week Introduction
• Video : Part of Speech Tagging
• Reading : Part of Speech Tagging
• Lab : Lecture Notebook - Working with text files
• Video : Markov Chains
• Reading : Markov Chains
• Video : Markov Chains and POS Tags
• Reading : Markov Chains and POS Tags
• Video : Hidden Markov Models
• Reading : Hidden Markov Models
• Video : Calculating Probabilities
• Reading : Calculating Probabilities
• Video : Populating the Transition Matrix
• Reading : Populating the Transition Matrix
• Video : Populating the Emission Matrix
• Reading : Populating the Emission Matrix
• Lab : Lecture Notebook - Working with tags and Numpy
• Video : The Viterbi Algorithm
• Reading : The Viterbi Algorithm
• Video : Viterbi: Initialization
• Reading : Viterbi: Initialization
• Video : Viterbi: Forward Pass
• Reading : Viterbi: Forward Pass
• Video : Viterbi: Backward Pass
• Reading : Viterbi: Backward Pass
• Video : Week Conclusion

Lecture Notes (Optional)

• Reading : Lecture Notes W2

Practice Quiz

• Practice Quiz : Part of Speech Tagging

Assignment: Part of Speech Tagging

• Programming Assignment : Part of Speech Tagging

Week 3

Lecture: Autocomplete

• Video : Week Introduction
• Video : N-Grams: Overview
• Reading : N-Grams: Overview
• Video : N-grams and Probabilities
• Reading : N-grams and Probabilities
• Video : Sequence Probabilities
• Reading : Sequence Probabilities
• Video : Starting and Ending Sentences
• Reading : Starting and Ending Sentences
• Lab : Lecture notebook: Corpus preprocessing for N-grams
• Video : The N-gram Language Model
• Reading : The N-gram Language Model
• Video : Language Model Evaluation
• Lab : Lecture notebook: Building the language model
• Reading : Language Model Evaluation
• Video : Out of Vocabulary Words
• Reading : Out of Vocabulary Words
• Video : Smoothing
• Reading : Smoothing
• Lab : Lecture notebook: Language model generalization
• Video : Week Summary
• Reading : Week Summary
• Video : Week Conclusion

Lecture Notes (Optional)

• Reading : Lecture Notes W3

Practice Quiz

• Practice Quiz : Autocomplete

Assignment: Autocomplete

• Programming Assignment : Autocomplete

Week 4

Lecture: Word Embeddings

• Video : Week Introduction
• Video : Overview
• Reading : Overview
• Video : Basic Word Representations
• Reading : Basic Word Representations
• Video : Word Embeddings
• Reading : Word Embeddings
• Video : How to Create Word Embeddings
• Reading : How to Create Word Embeddings?
• Video : Word Embedding Methods
• Reading : Word Embedding Methods
• Video : Continuous Bag-of-Words Model
• Reading : Continuous Bag-of-Words Model
• Video : Cleaning and Tokenization
• Reading : Cleaning and Tokenization
• Video : Sliding Window of Words in Python
• Reading : Sliding Window of Words in Python
• Video : Transforming Words into Vectors
• Reading : Transforming Words into Vectors
• Lab : Lecture Notebook - Data Preparation
• Video : Architecture of the CBOW Model
• Reading : Architecture of the CBOW Model
• Video : Architecture of the CBOW Model: Dimensions
• Reading : Architecture of the CBOW Model: Dimensions
• Video : Architecture of the CBOW Model: Dimensions 2
• Reading : Architecture of the CBOW Model: Dimensions 2
• Video : Architecture of the CBOW Model: Activation Functions
• Reading : Architecture of the CBOW Model: Activation Functions
• Lab : Lecture Notebook - Intro to CBOW model
• Video : Training a CBOW Model: Cost Function
• Reading : Training a CBOW Model: Cost Function
• Video : Training a CBOW Model: Forward Propagation
• Reading : Training a CBOW Model: Forward Propagation
• Video : Training a CBOW Model: Backpropagation and Gradient Descent
• Reading : Training a CBOW Model: Backpropagation and Gradient Descent
• Lab : Lecture Notebook - Training the CBOW model
• Video : Extracting Word Embedding Vectors
• Reading : Extracting Word Embedding Vectors
• Lab : Lecture Notebook - Word Embeddings
• Video : Evaluating Word Embeddings: Intrinsic Evaluation
• Reading : Evaluating Word Embeddings: Intrinsic Evaluation
• Video : Evaluating Word Embeddings: Extrinsic Evaluation
• Reading : Evaluating Word Embeddings: Extrinsic Evaluation
• Lab : Lecture notebook: Word embeddings step by step
• Video : Conclusion
• Reading : Conclusion
• Video : Week Conclusion

Lecture Notes (Optional)

• Reading : Lecture Notes W4

Practice Quiz

• Practice Quiz : Word Embeddings

End of access to Lab Notebooks

• Reading : [IMPORTANT] Reminder about end of access to Lab Notebooks

Assignment: Word Embeddings

• Programming Assignment : Word Embeddings

Acknowledgments

• Reading : Acknowledgments

Natural Language Processing with Sequence Models

Week 1

Week 2

Week 3

Week 4

Natural Language Processing with Attention Models

Week 1

Week 2

Week 3

Week 4