Sentence-BERT for embeddings in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the shape of the embeddings produced by Sentence-BERT?

Given the following code snippet that uses Sentence-BERT to encode a list of sentences, what is the shape of the resulting embeddings array?

NLP

from sentence_transformers import SentenceTransformer
sentences = ['I love machine learning.', 'Sentence-BERT creates embeddings.']
model = SentenceTransformer('all-MiniLM-L6-v2')
embeddings = model.encode(sentences)
print(embeddings.shape)

A (2, 384)

B (384, 2)

C (2, 768)

D (768, 2)

💡 Hint

The 'all-MiniLM-L6-v2' model produces 384-dimensional embeddings for each sentence.

Sentence-BERT models like 'all-MiniLM-L6-v2' output embeddings with 384 dimensions. Since there are 2 sentences, the shape is (2, 384).

❓ Model Choice

intermediate

Which Sentence-BERT model is best for fast embedding generation on CPU?

You want to generate sentence embeddings quickly on a CPU with limited memory. Which Sentence-BERT model should you choose?

A 'bert-large-nli-stsb-mean-tokens' - large and accurate model

B 'distilbert-base-nli-stsb-mean-tokens' - medium speed model

C 'all-MiniLM-L6-v2' - small and fast model

D 'roberta-base-nli-stsb-mean-tokens' - medium size model

💡 Hint

Smaller models with fewer layers run faster on CPU.

'all-MiniLM-L6-v2' is designed to be lightweight and fast, making it ideal for CPU usage with limited memory.

❓ Hyperparameter

advanced

Which parameter affects the batch size during Sentence-BERT encoding?

When calling the encode() method of a Sentence-BERT model, which parameter controls how many sentences are processed at once?

A num_workers

B max_length

C device

D batch_size

💡 Hint

This parameter helps balance speed and memory usage.

The 'batch_size' parameter sets how many sentences are encoded in one go, affecting speed and memory.

❓ Metrics

advanced

What metric is commonly used to evaluate Sentence-BERT embeddings on semantic textual similarity tasks?

Which metric best measures how well Sentence-BERT embeddings capture sentence similarity on datasets like STS Benchmark?

A F1 score

B Cosine similarity correlation (Spearman's rho)

C Accuracy

D Mean squared error

💡 Hint

This metric measures rank correlation between predicted and true similarity scores.

Spearman's rho on cosine similarity scores is standard for evaluating semantic textual similarity.

🔧 Debug

expert

Why does this Sentence-BERT encoding code raise a RuntimeError?

Consider this code snippet: from sentence_transformers import SentenceTransformer model = SentenceTransformer('all-MiniLM-L6-v2') sentences = ['Hello world'] * 10000 embeddings = model.encode(sentences, device='cuda') It raises a RuntimeError: CUDA out of memory. What is the best way to fix this?

A Reduce batch_size in encode() to a smaller number like 32

B Remove device='cuda' to run on CPU instead

C Increase the number of sentences processed at once

D Use a larger GPU with more memory

💡 Hint

Large batches can exceed GPU memory limits.

Reducing batch_size lowers memory usage per batch, preventing CUDA out of memory errors.

Practice

1. What is the main purpose of Sentence-BERT embeddings in NLP?

easy

A. To count the number of words in a sentence

B. To translate sentences into different languages

C. To generate random sentences for data augmentation

D. To convert sentences into numbers that capture their meaning

Solution

1. Step 1: Understand Sentence-BERT's role

   Sentence-BERT creates embeddings, which are numbers representing sentence meaning.

2. Step 2: Compare options with Sentence-BERT's function

   Only To convert sentences into numbers that capture their meaning describes converting sentences into meaningful numbers, matching Sentence-BERT's purpose.

3. Final Answer:

   To convert sentences into numbers that capture their meaning -> Option D

4. Quick Check:

   Sentence-BERT embeddings = meaningful numbers [OK]

Hint: Remember: embeddings = numbers capturing meaning [OK]

Common Mistakes:

• Confusing embeddings with translation
• Thinking embeddings count words
• Assuming embeddings generate sentences

2. Which Python code snippet correctly loads a pre-trained Sentence-BERT model using the sentence-transformers library?

easy

A. from sentence_transformers import SentenceTransformer
model = SentenceTransformer('all-MiniLM-L6-v2')

B. import sentence_transformers
model = sentence_transformers.load('all-MiniLM-L6-v2')

C. from transformers import SentenceBert
model = SentenceBert.load('all-MiniLM-L6-v2')

D. import sbert
model = sbert.SentenceTransformer('all-MiniLM-L6-v2')

Solution

1. Step 1: Recall correct import and model loading syntax

   The sentence-transformers library uses 'from sentence_transformers import SentenceTransformer' and then creates a model instance with the model name.

2. Step 2: Check each option for correctness

   from sentence_transformers import SentenceTransformer model = SentenceTransformer('all-MiniLM-L6-v2') matches the correct syntax. Options A, B, and D use incorrect imports or methods.

3. Final Answer:

   from sentence_transformers import SentenceTransformer model = SentenceTransformer('all-MiniLM-L6-v2') -> Option A

4. Quick Check:

   Correct import and model load = from sentence_transformers import SentenceTransformer model = SentenceTransformer('all-MiniLM-L6-v2') [OK]

Hint: Use 'from sentence_transformers import SentenceTransformer' [OK]

Common Mistakes:

• Using wrong import statements
• Calling non-existent load methods
• Confusing transformers library with sentence-transformers

3. Given the code below, what is the output shape of embeddings?

from sentence_transformers import SentenceTransformer
model = SentenceTransformer('all-MiniLM-L6-v2')
sentences = ['Hello world', 'How are you?']
embeddings = model.encode(sentences)
print(embeddings.shape)

medium

A. (384, 2)

B. (2, 384)

C. (2, 768)

D. (1, 384)

Solution

1. Step 1: Understand input and output of model.encode()

   Input is 2 sentences, so output embeddings will have 2 rows, one per sentence.

2. Step 2: Know embedding dimension of 'all-MiniLM-L6-v2'

   This model produces embeddings of size 384 per sentence.

3. Final Answer:

   (2, 384) -> Option B

4. Quick Check:

   2 sentences x 384 dims = (2, 384) [OK]

Hint: Output shape = (number of sentences, embedding size) [OK]

Common Mistakes:

• Swapping dimensions in output shape
• Assuming embedding size is 768
• Forgetting batch size dimension

4. You run this code but get an error: AttributeError: module 'sentence_transformers' has no attribute 'load'. What is the likely cause?

import sentence_transformers
model = sentence_transformers.load('all-MiniLM-L6-v2')

medium

A. The model file is missing from local directory

B. The model name 'all-MiniLM-L6-v2' is incorrect

C. The sentence_transformers module does not have a 'load' function

D. You need to import SentenceTransformer class explicitly

Solution

1. Step 1: Analyze the error message

   The error says 'sentence_transformers' has no attribute 'load', meaning 'load' is not a valid function in this module.

2. Step 2: Understand correct usage

   The correct way is to import SentenceTransformer class and instantiate it with the model name, not use 'load'.

3. Final Answer:

   The sentence_transformers module does not have a 'load' function -> Option C

4. Quick Check:

   AttributeError means wrong function call [OK]

Hint: Use SentenceTransformer(), not load() [OK]

Common Mistakes:

• Calling non-existent 'load' method
• Not importing SentenceTransformer class
• Assuming model loads from local file by default

5. You want to find the most similar sentence to 'I love machine learning' from a list using Sentence-BERT embeddings. Which approach is best?

hard

A. Encode all sentences and query, then find the sentence with highest cosine similarity to the query embedding

B. Count common words between query and each sentence, pick the highest count

C. Use a pre-trained translation model to translate sentences before comparison

D. Encode only the query sentence and compare it to raw text sentences

Solution

1. Step 1: Understand how Sentence-BERT embeddings are used for similarity

   Sentence-BERT embeddings represent sentence meaning as vectors; similarity is measured by cosine similarity between vectors.

2. Step 2: Evaluate options for similarity search

   Encode all sentences and query, then find the sentence with highest cosine similarity to the query embedding correctly encodes all sentences and compares embeddings using cosine similarity. Other options do not use embeddings properly or rely on less effective methods.

3. Final Answer:

   Encode all sentences and query, then find the sentence with highest cosine similarity to the query embedding -> Option A

4. Quick Check:

   Embedding + cosine similarity = best similarity search [OK]

Hint: Compare embeddings with cosine similarity for best match [OK]

Common Mistakes:

• Comparing raw text instead of embeddings
• Using word count instead of semantic similarity
• Encoding only query, not all sentences