Vector Semantics and Embedding #
This page is a structured learning template. Replace the comments with clear explanations, examples, formulas, diagrams, and practical insights while keeping the Hugo shortcodes intact.
Learning Objectives #
- Explain how word meaning can be represented using vectors.
- Compare sparse representations such as TF-IDF with dense word embeddings.
- Describe the intuition behind Skip-gram, CBOW, and GloVe.
- Interpret similarity and neighbourhood relationships in an embedding space.
Chapter Map #
| Section | Topic | Status |
|---|---|---|
| 1 | Lexical Semantics | ☐ |
| 2 | Vector Semantics | ☐ |
| 3 | Words and Vectors | ☐ |
| 4 | TF-IDF | ☐ |
| 5 | Word2Vec: Skip-gram and CBOW | ☐ |
| 6 | GloVe | ☐ |
| 7 | Visualising Embeddings | ☐ |
Big Picture #
1. Lexical Semantics ☆ #
Definition #
Intuition #
Key Concepts #
Formula or Model #
Worked Example #
Why It Matters in NLP #
Key Points to Remember #
2. Vector Semantics ☆ #
Definition #
Intuition #
Key Concepts #
Formula or Model #
Worked Example #
Why It Matters in NLP #
Key Points to Remember #
3. Words and Vectors ☆ #
Definition #
Intuition #
Key Concepts #
Formula or Model #
Worked Example #
Why It Matters in NLP #
Key Points to Remember #
4. TF-IDF ☆ #
Definition #
Intuition #
Key Concepts #
Formula or Model #
Worked Example #
Why It Matters in NLP #
Key Points to Remember #
5. Word2Vec: Skip-gram and CBOW ☆ #
Definition #
Intuition #
Key Concepts #
Formula or Model #
Worked Example #
Why It Matters in NLP #
Key Points to Remember #
6. GloVe ☆ #
Definition #
Intuition #
Key Concepts #
Formula or Model #
Worked Example #
Why It Matters in NLP #
Key Points to Remember #
7. Visualising Embeddings ☆ #
Definition #
Intuition #
Key Concepts #
Formula or Model #
Worked Example #
Why It Matters in NLP #
Key Points to Remember #
Practical Exploration #
Train or load word embeddings, calculate similarity, and visualise selected vectors.
# Add a minimal, well-commented Python example here.
Comparison Table #
| Concept or Model | Main Idea | Strength | Limitation | Typical Use |
|---|---|---|---|---|
Common Mistakes #
Practice Questions #
Key Takeaways #
Understanding Checklist #
- I can explain Lexical Semantics without referring to notes.
- I can explain Vector Semantics without referring to notes.
- I can explain Words and Vectors without referring to notes.
- I can explain TF-IDF without referring to notes.
- I can explain Word2Vec: Skip-gram and CBOW without referring to notes.
- I can explain GloVe without referring to notes.
- I can explain Visualising Embeddings without referring to notes.