Explore

Natural Language Processing with Probabilistic Models

Approx. 28 hours to complete

Save Course

Go to Course

Course Summary

This course explores probabilistic models in natural language processing (NLP) and covers topics such as language modeling, part-of-speech tagging, and sequence labeling.

Key Learning Points

Learn about the fundamentals of probabilistic models in NLP
Understand how to apply these models to various NLP tasks
Gain insight into the latest research in this field

Learning Outcomes

Ability to apply probabilistic models to NLP tasks
Understanding of the latest research in the field
Improved skills in machine learning and data analysis

Prerequisites or good to have knowledge before taking this course

Basic knowledge of machine learning and statistics
Familiarity with programming languages such as Python

Course Difficulty Level

Intermediate

Course Format

Online
Self-paced

Similar Courses

Applied Natural Language Processing
Deep Learning for Natural Language Processing

Related Education Paths

Related Books

Description

In Course 2 of the Natural Language Processing Specialization, offered by deeplearning.ai, 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 important 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. Please make sure that you’re comfortable programming in Python and have a basic knowledge of machine learning, matrix multiplications, and conditional probability. 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, and even built a chatbot! 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.

Outline

Autocorrect
Intro to Course 2
Overview
Autocorrect
Building the model
Building the model II
Minimum edit distance
Minimum edit distance algorithm
Minimum edit distance algorithm II
Minimum edit distance algorithm III
Connect with your mentors and fellow learners on Slack!
Overview
Autocorrect
Building the model
Building the model II
Minimum edit distance
Minimum edit distance algorithm
Minimum edit distance algorithm II
Minimum edit distance III
How to Refresh your Workspace

Part of Speech Tagging and Hidden Markov Models
Part of Speech Tagging
Markov Chains
Markov Chains and POS Tags
Hidden Markov Models
Calculating Probabilities
Populating the Transition Matrix
Populating the Emission Matrix
The Viterbi Algorithm
Viterbi: Initialization
Viterbi: Forward Pass
Viterbi: Backward Pass
Part of Speech Tagging
Markov Chains
Markov Chains and POS Tags
Hidden Markov Models
Calculating Probabilities
Populating the Transition Matrix
Populating the Emission Matric
The Viterbi Algorithm
Viterbi Initialization
Viterbi: Forward Pass
Viterbi: Backward Pass

Autocomplete and Language Models
N-Grams: Overview
N-grams and Probabilities
Sequence Probabilities
Starting and Ending Sentences
The N-gram Language Model
Language Model Evaluation
Out of Vocabulary Words
Smoothing
Week Summary
N-Grams Overview
N-grams and Probabilities
Sequence Probabilities
Starting and Ending Sentences
The N-gram Language Model
Language Model Evaluation
Out of Vocabulary Words
Smoothing
Week Summary

Word embeddings with neural networks
Overview
Basic Word Representations
Word Embeddings
How to Create Word Embeddings
Word Embedding Methods
Continuous Bag-of-Words Model
Cleaning and Tokenization
Sliding Window of Words in Python
Transforming Words into Vectors
Architecture of the CBOW Model
Architecture of the CBOW Model: Dimensions
Architecture of the CBOW Model: Dimensions 2
Architecture of the CBOW Model: Activation Functions
Training a CBOW Model: Cost Function
Training a CBOW Model: Forward Propagation
Training a CBOW Model: Backpropagation and Gradient Descent
Extracting Word Embedding Vectors
Evaluating Word Embeddings: Intrinsic Evaluation
Evaluating Word Embeddings: Extrinsic Evaluation
Conclusion
Basic Word Representations
Word Embeddings
How to Create Word Embeddings?
Word Embedding Methods
Continuous Bag of Words Model
Cleaning and Tokenization
Sliding Window of words in Python
Transforming Words into Vectors
Architecture for the CBOW Model
Architecture of the CBOW Model: Dimensions
Architecture of the CBOW Model: Dimensions
Architecture of the CBOW Model: Activation Functions
Training a CBOW Model: Cost Function
Training a CBOW Model: Forward Propagation
Training a CBOW Model: Backpropagation and Gradient Descent
Extracting Word Embedding Vectors
Evaluating Word Embeddings: Intrinsic Evaluation
Evaluating Word Embeddings: Extrinsic Evaluation
Conclusion
Acknowledgments

Summary of User Reviews

Discover how to apply probabilistic models to natural language processing with this course on Coursera. Students have given high praise for the course, citing its comprehensive curriculum and engaging instructors. However, some users have mentioned that the course can be challenging for those without a strong math background.

Key Aspect Users Liked About This Course

Comprehensive curriculum

Pros from User Reviews

Engaging and knowledgeable instructors
In-depth exploration of probabilistic models
Real-world applications of NLP techniques
Helpful assignments and quizzes

Cons from User Reviews

Requires a strong math background
Some sections can be challenging for beginners
Limited interaction with instructors
Lack of practical applications in some areas

Recommended for you

Data Science: Natural Language Processing (NLP) in Python

Applications: decrypting ciphers, spam detection, sentiment analysis, article spinners, and latent semantic analysis. All the materials for this course are FREE....

Save Course

Implementing Deep Learning Algorithms with TensorFlow 2.0

Build and train Deep Learning neural networks with TensorFlow 2. Deep Learning has caused the revival of Artificial Intelligence. 0. About the Author...

Save Course

Applying Machine Learning to your Data with GCP

In this module, we define what Machine Learning is and how it can benefit your business. PREREQUISITES • Exploring and Preparing your Data...

Save Course

Text Retrieval and Search Engines

This course will cover search engine technologies, which play an important role in any data mining applications involving text data for two reasons....

Save Course