Library
Cuantum trackFull access

NLP with Transformers: Fundamentals and Core Applications

12 chapters and 67 canonical sections synced from the Cuantum content database.

Author
Cuantum Tech.
Chapters
12
Reading time
~ 16h
Level
Professional
Language
English
Edition
2025
Your progress0%
Start reading

Chapters & sections

12 chapters - 67 sections

Chapter 1: Introduction to NLP and Its Evolution

0/5
1.1 What is NLP?44m1.2 Historical Development of NLP26m1.3 Traditional Approaches in NLP22m1.4 Practical Exercises for Chapter 15mChapter 1 Summary3m

Chapter 2: Fundamentals of Machine Learning for

0/6
2.1 Basics of Machine Learning for Text24m2.2 Neural Networks in NLP35m2.3 Word Embeddings: Word2Vec, GloVe, and FastText48m2.4 Introduction to Transformer-based Embeddings50mPractical Exercises for Chapter 26mChapter Summary3m

Chapter 3: Attention and the Rise of Transformers

0/6
3.1 Challenges with RNNs and CNNs in NLP37m3.2 Understanding Attention Mechanisms41m3.3 Self-Attention and Multi-Head Attention32m3.4 Sparse Attention for Efficiency42mPractical Exercises for Chapter 36mChapter 3 Summary3m

Quiz Part I

0/2
Questions3mAnswers3m

Chapter 4: The Transformer Architecture

0/6
4.1 The "Attention Is All You Need" Paper19m4.2 Encoder-Decoder Framework Explained18m4.3 Positional Encoding and Its Importance29m4.4 Comparisons with Traditional Architectures26mPractical Exercises for Chapter 46mChapter Summary3m

Chapter 5: Key Transformer Models and Innovations

0/6
5.1 BERT and Variants (RoBERTa, DistilBERT)49m5.2 GPT and Autoregressive Transformers68m5.3 Multimodal Transformers: CLIP, DALL-E36m5.4 Specialized Models: BioBERT, LegalBERT19mPractical Exercises for Chapter 55mChapter Summary3m

Quiz Part II

0/2
Questions2mAnswers2m

Chapter 6: Core NLP Applications

0/5
6.1 Sentiment Analysis46m6.2 Named Entity Recognition (NER)49m6.3 Text Classification50mPractical Exercises for Chapter 66mChapter 6 Summary3m

Project 1: Sentiment Analysis with BERT

0/10
1. Why Sentiment Analysis?3m2. Why Use BERT?2m3. Project Overview1m4. Step 1: Preparing the Environment1m5. Step 2: Loading and Exploring the Dataset1m6. Step 3: Tokenizing the Dataset1m7. Step 4: Fine-Tuning BERT1m8. Step 5: Evaluating the Model1m9. Step 6: Using the Model for Prediction1m10. Conclusion2m

Project 2: News Categorization Using BERT

0/9
1. Why BERT for News Categorization?4m2. What Will You Learn?2m3. Step 1: Setting Up the Environment1m4. Step 2: Loading and Preparing the Dataset2m5. Preprocess the Dataset2m6. Step 3: Fine-Tuning BERT for News Categorization4m7. Step 4: Evaluating the Model2m8. Step 5: Testing with New Data2mConclusion2m

Project 3: Customer Feedback Analysis Using Sentiment Analysis

0/8
1. Why Sentiment Analysis?3m2. What Will You Learn?1m3. Step 1: Setting Up the Environment1m4. Step 2: Loading and Preparing the Dataset4m5. Step 3: Fine-Tuning BERT for Sentiment Analysis4m6. Step 4: Evaluating the Model2m7. Step 5: Testing with Real Customer Feedback2mConclusion2m

Quiz Part III

0/2
Questions3mAnswers Key1m