Course
Natural Language Processing
52 hours 58 minutes
Credits: 3 Credits
Description
This course teaches learners how to understand and apply natural language processing techniques across the full NLP pipeline. Starting from text preprocessing and feature engineering, learners progress through machine learning for NLP, deep learning architectures, transformer models and BERT, and advanced NLP development using Hugging Face and LLMs for classification, translation, summarization, and fine-tuning.
What Students Will Learn
Chapter 1: NLP Foundations & Text Preprocessing
- Getting Started with NLP
- Introduction to Regular Expressions
- Fundamentals of NLP: Preprocessing Text Using NLTK & SpaCy
- Text Mining and Analytics: Pattern Matching & Information Extraction
- Regex Parsing with NLP Lab: Classic Texts
Chapter 2: Text Representation & Feature Engineering
- Fundamentals of NLP: Representing Text as Numeric Features
- Fundamentals of NLP: Word Embeddings to Capture Relationships in Text
- Lab: Bag of Words
- Lab: News Analysis with TF-IDF
- Lab: Analyze a Speech using Word Embeddings
Chapter 3: Machine Learning for NLP & Sentiment Analysis
- Fundamentals of NLP: Rule-based Models for Sentiment Analysis
- Text Mining and Analytics: Machine Learning for Natural Language Processing
- Text Mining and Analytics: Natural Language Processing Libraries
- Text Mining and Analytics: Hotel Reviews Sentiment Analysis
- Portfolio Project: Analyze Texts With NLP
- Final Exam: Natural Language Processing Fundamentals
Chapter 4: Deep Learning for NLP
- Natural Language Processing Using Deep Learning
- Deep Learning for NLP: Neural Network Architectures
- Deep Learning for NLP: Memory-based Networks
- Deep Learning for NLP: Transfer Learning
- Deep Learning for NLP: GitHub Bug Prediction Analysis
- Natural Language Processing
- Final Exam: Natural Language Processing
Chapter 5: Transformers & Advanced NLP
- Attention-based Models and Transformers for Natural Language Processing
- Advanced NLP: Introduction to BERT
- Using Out-of-the-Box Transformer Models for Natural Language Processing
- Advanced NLP: Language Translation Using Transformer Model
Chapter 6: NLP with LLMs & Hugging Face
- NLP with LLMs: Working with Tokenizers in Hugging Face
- NLP with LLMs: Hugging Face Classification, QnA, & Text Generation Pipelines
- NLP with LLMs: Language Translation, Summarization, & Semantic Similarity
- NLP with LLMs: Fine-tuning Models for Classification & Question Answering
- NLP with LLMs: Fine-tuning Models for Language Translation, & Summarization
- Natural Language Processing and LLMs
- Final Exam: Architecting LLMs for Your Technical Solutions
Optional
- NLP Case Studies: News Scraping Translation & Summarization
- NLP Case Studies: Article Text Comprehension & Question Answering
- NLP Case Studies: Developing an AI Chatbot
- Generating Text With Deep Learning Cheatsheet
- Bag Of Words Language Model Cheatsheet
- Introduction to Regular Expressions Cheatsheet
- Word Embeddings Cheatsheet
- Getting Started with NLP Cheatsheet
- Text Preprocessing with NLTK Cheatsheet
Overall Learning Outcomes
- Preprocess and extract patterns from text using NLTK, SpaCy, and regular expressions
- Represent text as numeric features using bag-of-words, TF-IDF, and word embeddings
- Apply rule-based and machine learning models for sentiment analysis and NLP tasks
- Use NLP libraries to build and evaluate text mining and analytics solutions
- Implement deep learning architectures including neural networks, memory-based networks, and transfer learning for NLP
- Build and evaluate transformer and attention-based models for NLP tasks
- Apply BERT and out-of-the-box transformer models for language understanding and translation
- Use Hugging Face tokenizers and pipelines for classification, question answering, and text generation
- Fine-tune LLMs for classification, question answering, language translation, and summarization