Sentence-BERT for embeddings in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is Sentence-BERT (SBERT)?

Sentence-BERT is a model that creates meaningful sentence embeddings by fine-tuning BERT with a siamese network structure, enabling efficient comparison of sentence meanings.

beginner

Why is Sentence-BERT better than vanilla BERT for sentence similarity tasks?

SBERT produces fixed-size sentence embeddings that can be compared quickly using cosine similarity, while vanilla BERT requires expensive pairwise token-level comparisons.

intermediate

How does SBERT generate embeddings for two sentences?

SBERT uses a siamese network to encode each sentence separately into vectors, then compares these vectors using simple distance metrics like cosine similarity.

beginner

What is a common use case for Sentence-BERT embeddings?

SBERT embeddings are used for tasks like semantic search, clustering similar sentences, and paraphrase detection by comparing sentence meanings efficiently.

beginner

What metric is typically used to compare SBERT embeddings?

Cosine similarity is commonly used to measure how close two SBERT sentence embeddings are in meaning.

What does Sentence-BERT primarily produce?

A Named entity labels

B Word-level token embeddings

C Fixed-size sentence embeddings

D Part-of-speech tags

Sentence-BERT creates fixed-size vectors representing whole sentences for easy comparison.

Which architecture does SBERT use to encode sentence pairs?

A Siamese network

B Recurrent neural network

C Convolutional neural network

D Transformer decoder only

SBERT uses a siamese network to encode sentences separately but in parallel.

Why is cosine similarity used with SBERT embeddings?

A It counts the number of matching words

B It measures the angle between vectors, showing semantic similarity

C It measures Euclidean distance only

D It normalizes sentence length

Cosine similarity measures how close two vectors point in the same direction, indicating similar meaning.

Which task is NOT a typical use case for SBERT embeddings?

A Image classification

B Semantic search

C Sentence clustering

D Paraphrase detection

SBERT embeddings are for text tasks, not image classification.

What problem does SBERT solve compared to vanilla BERT for sentence similarity?

A Inability to process sentences

B Lack of word embeddings

C Poor spelling correction

D High computational cost of pairwise token comparisons

SBERT reduces computation by encoding sentences separately, avoiding costly token-level comparisons.

Explain how Sentence-BERT creates embeddings and why this is useful for comparing sentence meanings.

Think about how SBERT avoids comparing tokens directly.

Describe common applications where Sentence-BERT embeddings improve performance.

Consider tasks that need quick understanding of sentence meaning.

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