Visualizing embeddings (t-SNE) in NLP - Model Pipeline Trace

Model Pipeline - Visualizing embeddings (t-SNE)

This pipeline shows how word embeddings from text data are transformed and visualized using t-SNE, a method that helps us see high-dimensional data in 2D. It helps us understand how similar words group together.

Data Flow - 5 Stages

1Raw Text Data

1000 sentences x variable length→Collect sentences containing words→1000 sentences x variable length

"The cat sat on the mat."

↓

2Tokenization

1000 sentences x variable length→Split sentences into words (tokens)→1000 sentences x average 10 tokens

["The", "cat", "sat", "on", "the", "mat"]

↓

3Embedding Lookup

1000 sentences x 10 tokens→Convert each token to a 50-dimensional vector→1000 sentences x 10 tokens x 50 features

[[0.1, -0.2, ..., 0.05], ..., [0.3, 0.0, ..., -0.1]]

↓

4Average Pooling

1000 sentences x 10 tokens x 50 features→Average token vectors to get sentence embedding→1000 sentences x 50 features

[0.12, -0.05, ..., 0.07]

↓

5t-SNE Dimensionality Reduction

1000 sentences x 50 features→Reduce 50D embeddings to 2D for visualization→1000 sentences x 2 features

[[12.3, -5.6], [7.8, 3.4], ...]

Training Trace - Epoch by Epoch

Loss
1.0 |          *
0.9 |         * 
0.8 |        *  
0.7 |       *   
0.6 |      *    
0.5 |     **    
0.4 |    *      
    +------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	N/A	Initial embedding vectors generated; no training loss as embeddings are pre-trained.
2	0.75	N/A	t-SNE starts organizing points; loss decreases indicating better neighborhood preservation.
3	0.60	N/A	Clusters of similar words start to form in 2D space.
4	0.50	N/A	t-SNE converges; loss stabilizes and clusters become clearer.
5	0.48	N/A	Final embedding visualization ready; minimal loss improvement.

Prediction Trace - 4 Layers

Layer 1: Tokenization

Layer 2: Embedding Lookup

Layer 3: Average Pooling

Layer 4: t-SNE Dimensionality Reduction

Model Quiz - 3 Questions

What does the t-SNE step do in this pipeline?

A Reduces high-dimensional embeddings to 2D for visualization

B Converts words into vectors

C Splits sentences into words

D Averages token vectors

Key Insight

This visualization shows how t-SNE helps us understand complex word or sentence embeddings by reducing their dimensions to 2D. It reveals groups of similar meanings, making abstract data easier to grasp.

Practice

1. What is the main purpose of using t-SNE in visualizing word embeddings?

easy

A. To train word embeddings from raw text data

B. To increase the size of word embeddings for better accuracy

C. To reduce high-dimensional word vectors into 2D or 3D for easy visualization

D. To cluster words based on their frequency in the text

Solution

1. Step 1: Understand t-SNE's role in dimensionality reduction

   t-SNE reduces complex, high-dimensional data like word embeddings into 2D or 3D space for visualization.

2. Step 2: Differentiate from other tasks

   It does not train embeddings or cluster by frequency but helps visualize similarity by reducing dimensions.

3. Final Answer:

   To reduce high-dimensional word vectors into 2D or 3D for easy visualization -> Option C

4. Quick Check:

   t-SNE = dimensionality reduction for visualization [OK]

Hint: t-SNE = reduce dimensions to visualize complex data [OK]

Common Mistakes:

• Confusing t-SNE with training embeddings
• Thinking t-SNE increases data size
• Assuming t-SNE clusters by word frequency

2. Which of the following is the correct way to import t-SNE from scikit-learn in Python?

easy

A. from sklearn.manifold import TSNE

B. import sklearn.tsne as TSNE

C. from sklearn.embedding import tSNE

D. import tsne from sklearn

Solution

1. Step 1: Recall correct module for t-SNE in scikit-learn

   t-SNE is in the sklearn.manifold module and is imported as TSNE.

2. Step 2: Check syntax correctness

   from sklearn.manifold import TSNE uses correct syntax: from sklearn.manifold import TSNE. Others are invalid imports.

3. Final Answer:

   from sklearn.manifold import TSNE -> Option A

4. Quick Check:

   Correct import = from sklearn.manifold import TSNE [OK]

Hint: t-SNE is in sklearn.manifold, import as TSNE [OK]

Common Mistakes:

• Using wrong module like sklearn.embedding
• Incorrect import syntax
• Confusing lowercase and uppercase in import

3. Given this Python code snippet using t-SNE, what will be the shape of embeddings_2d?

from sklearn.manifold import TSNE
import numpy as np

embeddings = np.random.rand(100, 50)  # 100 words, 50 dimensions
model = TSNE(n_components=2, random_state=42)
embeddings_2d = model.fit_transform(embeddings)

medium

A. (100, 2)

B. (2, 100)

C. (50, 2)

D. (100, 50)

Solution

1. Step 1: Understand input shape and t-SNE output

   Input embeddings have shape (100, 50) meaning 100 samples with 50 features each.

2. Step 2: Check t-SNE output shape with n_components=2

   t-SNE reduces features to 2 dimensions, so output shape is (100, 2) -- 100 samples, 2 features.

3. Final Answer:

   (100, 2) -> Option A

4. Quick Check:

   Output shape = (samples, n_components) = (100, 2) [OK]

Hint: Output shape = (samples, n_components) in t-SNE [OK]

Common Mistakes:

• Confusing rows and columns in output shape
• Assuming output shape equals input shape
• Mixing up n_components with sample count

4. You run t-SNE on word embeddings but get a ValueError: "perplexity must be less than n_samples". What is the likely cause and fix?

medium

A. Input embeddings have wrong shape; reshape to (features, samples)

B. Perplexity is set too high; reduce it below the number of samples

C. Random state is missing; add random_state parameter

D. t-SNE requires normalized data; normalize embeddings first

Solution

1. Step 1: Understand perplexity parameter in t-SNE

   Perplexity controls neighborhood size and must be less than the number of samples.

2. Step 2: Identify cause of ValueError

   Error means perplexity is set equal or larger than sample count, which is invalid.

3. Step 3: Fix by lowering perplexity

   Reduce perplexity to a value smaller than the number of samples to fix the error.

4. Final Answer:

   Perplexity is set too high; reduce it below the number of samples -> Option B

5. Quick Check:

   Perplexity < n_samples to avoid error [OK]

Hint: Keep perplexity less than sample count in t-SNE [OK]

Common Mistakes:

• Changing input shape instead of perplexity
• Ignoring the perplexity limit
• Assuming normalization fixes this error

5. You want to visualize embeddings of 5000 words using t-SNE but notice the plot is very crowded and unclear. Which approach best improves visualization clarity?

hard

A. Apply t-SNE with n_components=50 to keep more dimensions

B. Increase perplexity to a very high value like 1000 to spread points out

C. Use raw high-dimensional embeddings without dimensionality reduction

D. Reduce the number of words by selecting a smaller subset before applying t-SNE

Solution

1. Step 1: Understand t-SNE limitations with large datasets

   t-SNE works best with small to medium data; large sets cause crowded plots and slow computation.

2. Step 2: Choose practical solution for clarity

   Reducing the dataset size by selecting fewer words improves plot clarity and speed.

3. Step 3: Evaluate other options

   Increasing perplexity too high or keeping many dimensions defeats t-SNE's purpose; raw embeddings are hard to visualize.

4. Final Answer:

   Reduce the number of words by selecting a smaller subset before applying t-SNE -> Option D

5. Quick Check:

   Smaller data = clearer t-SNE plots [OK]

Hint: Use smaller data subsets for clearer t-SNE plots [OK]

Common Mistakes:

• Setting perplexity too high
• Using too many dimensions in t-SNE
• Trying to visualize raw embeddings directly