Prep 3: NLP, Embeddings, and Vector Spaces

📋 Main Topics¶

• Introduction: What is NLP? & Challenges of Interpreting Human Language
• Text Preprocessing: Stemming, Lemmatization, and Stopwords
• Statistical Approaches: Text Classification with N-grams and Bag of Words
• Frequency Analysis: Zipf’s Law and TF-IDF
• Semantic Embeddings: Word2Vec, CBOW, and Skip-Gram
• Modern Search: Vector Spaces and Vector Search

🧠 Class Activity - Labs¶

• Lab 2: NLP

🦾 Recommended Material¶

Note: These are the highest-quality resources available. It is highly recommended to view the Visual Guides to understand the high-dimensional geometry of embeddings.

🌟 Visual & Conceptual Guides (Essential)¶

• 🎥 The Illustrated Word2Vec by Jay Alammar (The industry standard for visualizing Embeddings/CBOW)
• 🎥 Visualizing Word Vectors by Computerphile (Great conceptual intro to vector space)
• 📚 A Complete Guide to NLP by DeepLearning.AI

🔉 Audio & Overview¶

• 🎥 NotebookLM Podcast on NLP (24 minutes - Engaging Overview)
• 📚 PDF Version

More Material & Deep Dives¶

🔍 Vector Search & Databases¶

• 🎥 What is a Vector Database? by IBM Technology
• 📚 What is Vector Search? by Pinecone (Comprehensive industry guide)

🎓 Academic & History¶

• 🎥 Stanford CS224N: Intro and Word Vectors (Academic Gold Standard)
• 📚 A Beginner Guide to NLP by IBM
• 🎥 What is NLP by Google (5 min)
• 🎥 NLP History (3 min)