GloVe embeddings in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does GloVe stand for in GloVe embeddings?

GloVe stands for Global Vectors for Word Representation. It is a method to create word embeddings by capturing global word co-occurrence statistics.

intermediate

How does GloVe differ from Word2Vec in learning word embeddings?

GloVe uses a matrix factorization approach on the global word co-occurrence matrix, while Word2Vec learns embeddings by predicting words in local context windows using a neural network.

beginner

What is the main input data structure used by GloVe to learn embeddings?

GloVe uses a word co-occurrence matrix that counts how often pairs of words appear together in a large text corpus.

beginner

Why are GloVe embeddings useful in natural language processing tasks?

They capture semantic relationships between words by encoding how frequently words co-occur globally, helping models understand word meanings and similarities.

intermediate

What kind of mathematical operation does GloVe use to learn word vectors from the co-occurrence matrix?

GloVe performs matrix factorization by minimizing a weighted least squares objective to find word vectors that reconstruct the co-occurrence counts.

What is the main data structure GloVe uses to learn word embeddings?

A Word frequency list

B Part-of-speech tags

C Word co-occurrence matrix

D Dependency parse trees

GloVe learns embeddings by factorizing the word co-occurrence matrix, which counts how often word pairs appear together.

Which of the following best describes GloVe's approach?

A Matrix factorization of global co-occurrence counts

B Using recurrent neural networks

C Clustering words by frequency

D Predicting words from local context windows

GloVe uses matrix factorization on the global co-occurrence matrix, unlike Word2Vec which predicts words from local context.

What does a GloVe embedding vector represent?

A The frequency of a word in the corpus

B Semantic meaning based on global word co-occurrence

C The position of a word in a sentence

D The length of a word

GloVe embeddings capture semantic meaning by encoding how words co-occur globally in the corpus.

Which is a key advantage of GloVe embeddings?

A They capture global statistical information

B They require no training data

C They only consider immediate neighbors

D They are random vectors

GloVe embeddings capture global co-occurrence statistics, unlike some methods that only consider local context.

What kind of loss function does GloVe minimize during training?

A Mean absolute error

B Cross-entropy loss

C Hinge loss

D Weighted least squares loss

GloVe minimizes a weighted least squares loss to factorize the co-occurrence matrix effectively.

Explain in your own words how GloVe embeddings are created from a text corpus.

Think about how often words appear together and how that information is turned into vectors.

Describe the main difference between GloVe and Word2Vec embeddings.

Focus on what data each method uses to learn embeddings.

Practice

1. What is the main purpose of GloVe embeddings in natural language processing?

easy

A. To generate random text based on input

B. To translate text from one language to another

C. To count the frequency of words in a document

D. To convert words into numerical vectors that capture meaning and relationships

Solution

1. Step 1: Understand what embeddings do

   Embeddings convert words into numbers so machines can understand text.

2. Step 2: Identify GloVe's role

   GloVe embeddings specifically capture word meanings and relationships in vector form.

3. Final Answer:

   To convert words into numerical vectors that capture meaning and relationships -> Option D

4. Quick Check:

   GloVe = word vectors capturing meaning [OK]

Hint: Remember: embeddings = words to numbers showing meaning [OK]

Common Mistakes:

• Confusing embeddings with translation
• Thinking embeddings count word frequency
• Assuming embeddings generate text

2. Which of the following is the correct way to load pre-trained GloVe embeddings in Python using the gensim library?

easy

A. glove = gensim.models.FastText.load('glove.txt')

B. glove = gensim.models.Word2Vec.load('glove.txt')

C. glove = gensim.models.KeyedVectors.load_word2vec_format('glove.txt', binary=False)

D. glove = gensim.load('glove.txt')

Solution

1. Step 1: Recall GloVe loading method

   GloVe embeddings are loaded as KeyedVectors using load_word2vec_format with binary=False.

2. Step 2: Check options for correct syntax

   glove = gensim.models.KeyedVectors.load_word2vec_format('glove.txt', binary=False) uses the correct function and parameters for GloVe format.

3. Final Answer:

   glove = gensim.models.KeyedVectors.load_word2vec_format('glove.txt', binary=False) -> Option C

4. Quick Check:

   Use load_word2vec_format with binary=False for GloVe [OK]

Hint: Use load_word2vec_format with binary=False for GloVe files [OK]

Common Mistakes:

• Using Word2Vec.load for GloVe files
• Forgetting binary=False parameter
• Using FastText load for GloVe

3. Given the following Python code snippet using pre-trained GloVe embeddings, what will be the output?

from gensim.models import KeyedVectors

glove = KeyedVectors.load_word2vec_format('glove.6B.50d.txt', binary=False)
result = glove.similarity('king', 'queen')
print(round(result, 2))

medium

A. 0.00

B. 0.78

C. 1.00

D. -0.50

Solution

1. Step 1: Understand similarity method

   The similarity method returns a cosine similarity score between two word vectors, usually between 0 and 1 for related words.

2. Step 2: Interpret expected similarity for 'king' and 'queen'

   These words are closely related, so the similarity is high but less than 1, typically around 0.78.

3. Final Answer:

   0.78 -> Option B

4. Quick Check:

   Similarity('king','queen') ≈ 0.78 [OK]

Hint: Related words have similarity close to but less than 1 [OK]

Common Mistakes:

• Assuming similarity is always 1 for related words
• Confusing similarity with distance
• Expecting negative similarity for related words

4. You try to find the vector for the word 'unseenword' using GloVe embeddings with this code:

vector = glove['unseenword']

But it raises a KeyError. What is the best way to fix this error?

medium

A. Check if the word exists in the embeddings before accessing it

B. Use glove.get_vector('unseenword') without checking

C. Ignore the error and continue

D. Restart the Python kernel

Solution

1. Step 1: Understand cause of KeyError

   The word 'unseenword' is not in the GloVe vocabulary, so direct access raises KeyError.

2. Step 2: Use safe access method

   Check if the word exists using 'if word in glove' before accessing to avoid errors.

3. Final Answer:

   Check if the word exists in the embeddings before accessing it -> Option A

4. Quick Check:

   Check word presence before access to avoid KeyError [OK]

Hint: Always check word in embeddings before access [OK]

Common Mistakes:

• Trying to access vectors without checking existence
• Ignoring errors instead of handling them
• Restarting kernel does not fix missing words

5. You want to improve a text classification model by using GloVe embeddings. Which approach best combines GloVe vectors with your model to handle words not in the GloVe vocabulary?

hard

A. Initialize an embedding layer with GloVe vectors and allow it to be trainable with random vectors for unknown words

B. Use only GloVe vectors and ignore unknown words during training

C. Replace unknown words with a fixed zero vector and freeze the embedding layer

D. Train a new embedding from scratch without using GloVe

Solution

1. Step 1: Understand embedding layer initialization

   Initializing with GloVe vectors provides good starting word representations.

2. Step 2: Handle unknown words and training

   Allowing the embedding layer to be trainable lets the model learn vectors for unknown words starting from random initialization.

3. Final Answer:

   Initialize an embedding layer with GloVe vectors and allow it to be trainable with random vectors for unknown words -> Option A

4. Quick Check:

   Trainable embeddings + GloVe + random unknown vectors = best practice [OK]

Hint: Use trainable embeddings with GloVe plus random unknown vectors [OK]

Common Mistakes:

• Ignoring unknown words instead of learning their vectors
• Freezing embeddings and losing adaptability
• Not using pre-trained GloVe vectors at all