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.