Natural Language Processing with Sequence Models
In Course 3 of the Natural Language Processing Specialization, you will: a) Train a neural network with word embeddings to perform sentiment analysis of tweets, b) Generate synthetic Shakespeare text using a Gated Recurrent Unit (GRU) language model, c) Train a recurrent neural network to perform named entity recognition (NER) using LSTMs with linear layers, and d) Use so-called ‘Siamese’ LSTM models to compare questions in a corpus and identify those that are worded differently but have the same meaning. By the end of this Specialization, you will have designed NLP applications that perfo
Buy Now AED 170.99 + VAT
Monthly Subscription Starting at AED 99 + VAT
- Level Professional
- Duration 24 hours
- Course by DeepLearning.AI
-
Offered by
About
In Course 3 of the Natural Language Processing Specialization, you will: a) Train a neural network with GLoVe word embeddings to perform sentiment analysis of tweets, b) Generate synthetic Shakespeare text using a Gated Recurrent Unit (GRU) language model, c) Train a recurrent neural network to perform named entity recognition (NER) using LSTMs with linear layers, and d) Use so-called "Siamese' LSTM models to compare questions in a corpus and identify those that are worded differently but have the same meaning. 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.Modules
Introduction to Neural Networks and TensorFlow
-
5
Videos
-
4
Readings
-
1
ExternalTool
-
1
Lab
1
External Tool
- [IMPORTANT] Have questions, issues or ideas? Join our community on Discourse!
1
Labs
- Introduction to TensorFlow
5
Videos
- Course 3 Introduction
- Lesson Introduction
- Neural Networks for Sentiment Analysis
- Dense Layers and ReLU
- Embedding and Mean Layers
4
Readings
- Lesson Introduction Clarification
- Neural Networks for Sentiment Analysis
- Dense Layers and ReLU
- Embedding and Mean Layers
Practice Assignment: Classification Using Deep Neural Networks
-
1
Readings
-
1
Programming
- Sentiment with Deep Neural Networks
1
Readings
- (Optional) Downloading your Notebook, Downloading your Workspace and Refreshing your Workspace
N-grams vs. Sequence Models
-
10
Videos
-
9
Readings
-
3
Lab
3
Labs
- Hidden State Activation
- Vanilla RNNs, GRUs and the scan function
- Calculating Perplexity
10
Videos
- Lesson Introduction
- Traditional Language models
- Recurrent Neural Networks
- Applications of RNNs
- Math in Simple RNNs
- Cost Function for RNNs
- Implementation Note
- Gated Recurrent Units
- Deep and Bi-directional RNNs
- Week Conclusion
9
Readings
- Traditional Language models
- Recurrent Neural Networks
- Application of RNNs
- Math in Simple RNNs
- Cost Function for RNNs
- Implementation Note
- Gated Recurrent Units
- Deep and Bi-directional RNNs
- Calculating Perplexity
Lecture Notes (Optional)
-
1
Readings
1
Readings
- Lecture Notes W1
Practice Quiz
-
1
Assignment
1
Assignment
- RNNs for Language Modelling
Assignment: Deep N-grams
-
1
Programming
- Deep N-grams
LSTMs and Named Entity Recognition
-
8
Videos
-
8
Readings
-
1
Lab
1
Labs
- Vanishing Gradients
8
Videos
- Week Introduction
- RNNs and Vanishing Gradients
- Introduction to LSTMs
- LSTM Architecture
- Introduction to Named Entity Recognition
- Training NERs: Data Processing
- Computing Accuracy
- Week Conclusion
8
Readings
- RNNs and Vanishing Gradients
- (Optional) Intro to optimization in deep learning: Gradient Descent
- Introduction to LSTMs
- LSTM Architecture
- Introduction to Named Entity Recognition
- Training NERs: Data Processing
- Long Short-Term Memory (Deep Learning Specialization C5)
- Computing Accuracy
Lecture Notes (Optional)
-
1
Readings
1
Readings
- Lecture Notes W2
Practice Quiz
-
1
Assignment
1
Assignment
- LSTMs and Named Entity Recognition
Assignment: Named Entity Recognition (NER)
-
1
Programming
- Named Entity Recognition (NER)
Siamese Networks
-
10
Videos
-
8
Readings
-
3
Lab
3
Labs
- Creating a Siamese Model
- Implementing the Modified Triplet Loss in TensorFlow
- Evaluate a Siamese Model
10
Videos
- Week Introduction
- Siamese Networks
- Architecture
- Cost Function
- Triplets
- Computing The Cost I
- Computing The Cost II
- One Shot Learning
- Training / Testing
- Week Conclusion
8
Readings
- Siamese Network
- Architecture
- Cost Function
- Triplets
- Computing the Cost I
- Computing the Cost II
- One Shot Learning
- Training / Testing
Lecture Notes (Optional)
-
1
Readings
1
Readings
- Lecture Notes W3
Practice Quiz
-
1
Assignment
1
Assignment
- Siamese Networks
Assignment: Question Duplicates
-
1
Programming
- Question Duplicates
Acknowledgments
-
1
Readings
1
Readings
- Acknowledgments
Auto Summary
Dive into the "Natural Language Processing with Sequence Models" course, part of Coursera's Data Science & AI domain. Led by Stanford's Younes Bensouda Mourri and Google's Łukasz Kaiser, this professional-level course covers sentiment analysis, named entity recognition, and synthetic text generation using advanced neural networks. Over 1440 minutes, you'll master NLP applications like question-answering and text summarization. Subscription options include Starter, Professional, and Paid. Ideal for professionals eager to enhance their NLP skills.
Younes Bensouda Mourri
Łukasz Kaiser