Semantic similarity with embeddings in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the sentence transformer model.

NLP

from sentence_transformers import SentenceTransformer
model = SentenceTransformer('[1]')

Drag options to blanks, or click blank then click option'

Abert-base-uncased

Bresnet50

Cgpt-3

Dall-MiniLM-L6-v2

Attempts:

3 left

💡 Hint

Common Mistakes

Using a model name meant for image tasks like 'resnet50'.

Using a general language model like 'bert-base-uncased' without sentence transformer wrapper.

The 'all-MiniLM-L6-v2' is a popular lightweight model for semantic similarity tasks using sentence transformers.

2fill in blank

medium

Complete the code to compute embeddings for a list of sentences.

NLP

sentences = ['I love machine learning', 'AI is fascinating']
embeddings = model.[1](sentences)

Drag options to blanks, or click blank then click option'

Aencode

Btransform

Cpredict

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'predict' which is not available in sentence transformers.

Using 'fit' which is for training, not embedding.

The 'encode' method computes embeddings for input sentences in sentence transformers.

3fill in blank

hard

Fix the error in computing cosine similarity between two embeddings.

NLP

from sklearn.metrics.pairwise import cosine_similarity
sim = cosine_similarity([emb1], [1])

Drag options to blanks, or click blank then click option'

Aemb2.reshape(-1)

Bemb2

Cemb2.tolist()

Demb2[0]

Attempts:

3 left

💡 Hint

Common Mistakes

Passing emb2[0] which is a scalar, causing shape errors.

Passing emb2.tolist() which may flatten incorrectly.

cosine_similarity expects 2D arrays, so embeddings should be wrapped in lists or arrays. Using 'emb2' as a list works correctly.

4fill in blank

hard

Fill both blanks to create a dictionary of sentence embeddings for sentences longer than 3 words.

NLP

sentences = ['I love AI', 'Machine learning is fun', 'Hello world']
embeddings = {sentence: model.[1]([sentence])[0] for sentence in sentences if len(sentence.[2]()) > 3}

Drag options to blanks, or click blank then click option'

Aencode

Bsplit

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'encode' for the second blank which is a string method.

Using 'split' for the first blank which is a model method.

We use 'encode' to get embeddings and 'split' to count words by splitting the sentence string.

5fill in blank

hard

Fill all three blanks to compute cosine similarity scores for pairs of sentences.

NLP

from sklearn.metrics.pairwise import cosine_similarity
sentences = ['AI is cool', 'I love AI']
embeddings = model.[1](sentences)
similarity_score = cosine_similarity(embeddings[[2]].reshape(1, -1), embeddings[[3]].reshape(1, -1))[0][0]

Drag options to blanks, or click blank then click option'

Aencode

B0

C1

Dpredict

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'predict' instead of 'encode' for embeddings.

Mixing up indices 0 and 1.

We encode sentences to get embeddings, then compare embedding 0 with embedding 1 using cosine similarity.

Practice

1. What does semantic similarity with embeddings help us do in natural language processing?

easy

A. Translate text from one language to another

B. Count the number of words in a sentence

C. Measure how similar the meanings of two texts are

D. Generate random sentences

Solution

1. Step 1: Understand semantic similarity

   Semantic similarity means checking how close the meanings of two texts are, not just the words.

2. Step 2: Role of embeddings

   Embeddings convert text into numbers that capture meaning, allowing comparison of texts by meaning.

3. Final Answer:

   Measure how similar the meanings of two texts are -> Option C

4. Quick Check:

   Semantic similarity = meaning comparison [OK]

Hint: Semantic similarity compares meanings, not word counts [OK]

Common Mistakes:

• Confusing similarity with word count
• Thinking embeddings translate text
• Assuming semantic similarity generates text

2. Which Python library is commonly used to compute cosine similarity between embeddings?

easy

A. matplotlib

B. scikit-learn

C. pandas

D. flask

Solution

1. Step 1: Identify cosine similarity function

   Cosine similarity is often computed using scikit-learn's metrics module.

2. Step 2: Check other libraries

   matplotlib is for plotting, pandas for data frames, flask for web apps, so they don't compute cosine similarity.

3. Final Answer:

   scikit-learn -> Option B

4. Quick Check:

   Cosine similarity = scikit-learn [OK]

Hint: Use scikit-learn for cosine similarity calculations [OK]

Common Mistakes:

• Using matplotlib for similarity
• Confusing pandas with similarity tools
• Thinking flask handles embeddings

3. What is the output of this Python code snippet?

from sklearn.metrics.pairwise import cosine_similarity
import numpy as np

emb1 = np.array([[1, 0, 0]])
emb2 = np.array([[0, 1, 0]])
sim = cosine_similarity(emb1, emb2)
print(sim[0][0])

medium

A. Error

B. 1.0

C. -1.0

D. 0.0

Solution

1. Step 1: Understand cosine similarity formula

   Cosine similarity measures the cosine of the angle between two vectors. Orthogonal vectors have similarity 0.

2. Step 2: Analyze given vectors

   emb1 is [1,0,0], emb2 is [0,1,0]. They are perpendicular, so similarity is 0.

3. Final Answer:

   0.0 -> Option D

4. Quick Check:

   Orthogonal vectors similarity = 0.0 [OK]

Hint: Orthogonal vectors have cosine similarity zero [OK]

Common Mistakes:

• Assuming similarity is 1 for any vectors
• Confusing dot product with cosine similarity
• Expecting error due to shape

4. Identify the error in this code that tries to compute semantic similarity:

from sklearn.metrics.pairwise import cosine_similarity

emb1 = [0.1, 0.2, 0.3]
emb2 = [0.1, 0.2, 0.3]
sim = cosine_similarity(emb1, emb2)
print(sim)

medium

A. emb1 and emb2 should be 2D arrays, not 1D lists

B. cosine_similarity function does not exist in sklearn

C. embeddings must be strings, not numbers

D. print statement syntax is incorrect

Solution

1. Step 1: Check input format for cosine_similarity

   cosine_similarity expects 2D arrays (like [[...]]), but emb1 and emb2 are 1D lists.

2. Step 2: Confirm other options

   cosine_similarity exists, embeddings are numeric vectors, and print syntax is correct in Python 3.

3. Final Answer:

   emb1 and emb2 should be 2D arrays, not 1D lists -> Option A

4. Quick Check:

   Input shape must be 2D arrays [OK]

Hint: cosine_similarity needs 2D arrays, not 1D lists [OK]

Common Mistakes:

• Passing 1D lists instead of 2D arrays
• Thinking embeddings must be text
• Misunderstanding print syntax

5. You have two sentences: "I love apples" and "I adore oranges". Using a pre-trained embedding model, you get vectors for both. Which approach best helps you find if these sentences have similar meaning?

hard

A. Calculate cosine similarity between their embeddings

B. Count common words between the sentences

C. Check if sentence lengths are equal

D. Compare the first letters of each word

Solution

1. Step 1: Understand semantic similarity goal

   We want to compare meanings, not just words or sentence length.

2. Step 2: Use embeddings and cosine similarity

   Pre-trained embeddings capture meaning; cosine similarity measures closeness of meanings numerically.

3. Final Answer:

   Calculate cosine similarity between their embeddings -> Option A

4. Quick Check:

   Meaning comparison = cosine similarity on embeddings [OK]

Hint: Use cosine similarity on embeddings for meaning comparison [OK]

Common Mistakes:

• Relying on word overlap only
• Using sentence length as similarity
• Comparing letters instead of meaning