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.