Visualizing embeddings (t-SNE) in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the main purpose of t-SNE in visualizing embeddings?

t-SNE helps to reduce high-dimensional data (like word embeddings) into 2 or 3 dimensions so we can see patterns and clusters easily on a simple plot.

beginner

Why can't we just plot embeddings directly without t-SNE?

Embeddings usually have many dimensions (like 100 or 300), which we can't visualize directly. t-SNE reduces these dimensions while keeping similar points close together.

beginner

What does it mean when points are close together in a t-SNE plot of embeddings?

Points close together mean their original embeddings are similar, so the words or items they represent are related or have similar meanings.

intermediate

What is a common challenge when using t-SNE for embedding visualization?

t-SNE can be slow on large datasets and sometimes shows different results each time because it uses randomness in its calculations.

intermediate

Name one alternative to t-SNE for visualizing embeddings.

UMAP is a popular alternative that is faster and often preserves more of the global structure in the data.

What does t-SNE primarily do with high-dimensional embeddings?

A Reduce dimensions to 2 or 3 for visualization

B Increase dimensions for better accuracy

C Convert embeddings into text

D Remove noise from embeddings

t-SNE reduces high-dimensional data to 2 or 3 dimensions so we can visualize it easily.

In a t-SNE plot, what does it mean if two points are far apart?

A They represent the same word

B Their embeddings are very different

C They have identical meanings

D They are errors in the data

Points far apart in t-SNE space usually mean their original embeddings are quite different.

Which of these is a limitation of t-SNE?

A It always produces the same output

B It increases data dimensions

C It can be slow on large datasets

D It removes important data features

t-SNE can be slow and sometimes produces different results due to randomness.

Which alternative method is known for faster embedding visualization than t-SNE?

A Linear Regression

B PCA

C K-Means

D UMAP

UMAP is a faster alternative to t-SNE for visualizing embeddings.

Why do we use 2D or 3D plots for embeddings?

A Because humans can easily understand 2D or 3D visuals

B Because embeddings only have 2 or 3 dimensions

C Because 2D plots increase embedding accuracy

D Because 3D plots remove noise

We reduce embeddings to 2D or 3D so humans can see and understand the data patterns.

Explain how t-SNE helps in understanding word embeddings.

Think about how we can see relationships between words visually.

Describe one limitation of t-SNE and a possible alternative method.

Consider speed and consistency issues.