Pre-trained embedding usage in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a pre-trained embedding in NLP?

A pre-trained embedding is a set of word or token vectors learned from a large text dataset before being used in a new task. It helps represent words as numbers that capture their meanings and relationships.

beginner

Why use pre-trained embeddings instead of training from scratch?

Pre-trained embeddings save time and resources because they already capture useful language patterns. They improve model performance, especially when you have limited data for your task.

beginner

Name two popular pre-trained embedding models.

Two popular pre-trained embedding models are Word2Vec and GloVe. Both learn word vectors from large text corpora but use different training methods.

intermediate

How do you use pre-trained embeddings in a neural network?

You load the pre-trained vectors and use them as the initial weights for the embedding layer in your neural network. You can keep them fixed or allow fine-tuning during training.

intermediate

What is fine-tuning in the context of pre-trained embeddings?

Fine-tuning means updating the pre-trained embedding weights slightly during your task's training to better fit your specific data and improve performance.

What is the main benefit of using pre-trained embeddings?

A They always produce random vectors

B They require more data to train

C They replace the need for a neural network

D They reduce training time and improve performance

Pre-trained embeddings reduce training time and improve performance by providing meaningful word representations learned from large datasets.

Which of these is NOT a popular pre-trained embedding model?

A RandomForest

B Word2Vec

C GloVe

D FastText

RandomForest is a machine learning algorithm, not a pre-trained embedding model.

What does fine-tuning pre-trained embeddings involve?

A Freezing the embeddings so they don't change

B Using embeddings only for testing

C Updating embeddings during training to fit new data

D Deleting embeddings after training

Fine-tuning means updating the embeddings during training to better fit the new task's data.

How are pre-trained embeddings usually integrated into a model?

A As the output layer

B As the initial weights of the embedding layer

C As the loss function

D As the optimizer

Pre-trained embeddings are loaded as the initial weights of the embedding layer in a neural network.

Which statement about pre-trained embeddings is true?

A They capture semantic relationships between words

B They always require training from scratch

C They cannot be used with neural networks

D They are only useful for image data

Pre-trained embeddings capture semantic relationships between words, helping models understand meaning.

Explain what pre-trained embeddings are and why they are useful in NLP tasks.

Think about how embeddings represent words and how pre-training helps.

Describe how you would use pre-trained embeddings in a neural network model and the role of fine-tuning.

Consider the embedding layer and training process.

Practice

1. What is the main benefit of using pre-trained embeddings in NLP tasks?

easy

A. They only work for images, not text.

B. They generate random word vectors for each run.

C. They replace the need for any model training.

D. They provide ready-made word meanings, saving training time.

Solution

1. Step 1: Understand what pre-trained embeddings are

   Pre-trained embeddings are word vectors learned from large text data before your task.

2. Step 2: Identify their benefit

   They save time because you don't train word meanings from scratch, improving efficiency.

3. Final Answer:

   They provide ready-made word meanings, saving training time. -> Option D

4. Quick Check:

   Pre-trained embeddings = ready-made word meanings [OK]

Hint: Pre-trained means already learned word meanings [OK]

Common Mistakes:

• Thinking embeddings generate random vectors each time
• Believing embeddings remove all model training
• Confusing embeddings with image features

2. Which Python code correctly loads a pre-trained embedding file named glove.txt into a dictionary called embeddings?

easy

A. embeddings = open('glove.txt').split()

B. embeddings = open('glove.txt').read()

C. embeddings = {line.split()[0]: list(map(float, line.split()[1:])) for line in open('glove.txt')}

D. embeddings = dict(open('glove.txt'))

Solution

1. Step 1: Understand the file format

   Each line has a word followed by numbers (vector components).

2. Step 2: Choose code that maps words to vectors

   embeddings = {line.split()[0]: list(map(float, line.split()[1:])) for line in open('glove.txt')} splits each line, uses first part as key, rest as float list values.

3. Final Answer:

   embeddings = {line.split()[0]: list(map(float, line.split()[1:])) for line in open('glove.txt')} -> Option C

4. Quick Check:

   Dictionary comprehension with split and float conversion = embeddings = {line.split()[0]: list(map(float, line.split()[1:])) for line in open('glove.txt')} [OK]

Hint: Use dict comprehension with split and float conversion [OK]

Common Mistakes:

• Using read() returns a string, not a dict
• Trying to split on file object directly
• Passing file object to dict() without processing

3. Given the code below, what will print(embeddings['cat']) output if glove.txt contains the line cat 0.1 0.2 0.3?

embeddings = {line.split()[0]: list(map(float, line.split()[1:])) for line in open('glove.txt')}
print(embeddings['cat'])

medium

A. [0.1, 0.2, 0.3]

B. 'cat 0.1 0.2 0.3'

C. ['cat', 0.1, 0.2, 0.3]

D. KeyError

Solution

1. Step 1: Understand dictionary comprehension

   Each word maps to a list of floats from the line after splitting.

2. Step 2: Check the key 'cat'

   It maps to [0.1, 0.2, 0.3] as floats in a list.

3. Final Answer:

   [0.1, 0.2, 0.3] -> Option A

4. Quick Check:

   embeddings['cat'] = float list [OK]

Hint: Split line, first word key, rest floats list [OK]

Common Mistakes:

• Expecting string instead of float list
• Confusing key with value
• Assuming KeyError without checking file content

4. The code below tries to load embeddings but causes type issues. What is the likely cause?

embeddings = {}
with open('glove.txt') as f:
    for line in f:
        word, vector = line.split()[0], line.split()[1:]
        embeddings[word] = vector
print(type(embeddings['dog'][0]))

medium

A. The file path 'glove.txt' is incorrect.

B. The vector values are strings, not floats, causing type issues.

C. The dictionary keys are not unique.

D. The print statement syntax is wrong.

Solution

1. Step 1: Analyze vector assignment

   Vector is assigned as list of strings from split, not converted to floats.

2. Step 2: Check print type

   Printing type of embeddings['dog'][0] shows string, not float, which may cause errors later.

3. Final Answer:

   The vector values are strings, not floats, causing type issues. -> Option B

4. Quick Check:

   Missing float conversion = The vector values are strings, not floats, causing type issues. [OK]

Hint: Convert vector strings to floats before storing [OK]

Common Mistakes:

• Ignoring need to convert strings to floats
• Assuming file path error without checking
• Thinking keys must be unique error

5. You want to use pre-trained embeddings in a text classification model. Which step is essential to correctly use these embeddings in your model's input layer?

hard

A. Map each word in your text to its embedding vector and create a matrix input.

B. Train embeddings from scratch ignoring pre-trained vectors.

C. Replace all words with their index positions only.

D. Use embeddings only for output layer predictions.

Solution

1. Step 1: Understand embedding usage in models

   Pre-trained embeddings provide vector representations for words to input into models.

2. Step 2: Identify correct input preparation

   Mapping words to their vectors and forming a matrix is needed to feed the model.

3. Final Answer:

   Map each word in your text to its embedding vector and create a matrix input. -> Option A

4. Quick Check:

   Embedding vectors as input = Map each word in your text to its embedding vector and create a matrix input. [OK]

Hint: Convert words to vectors matrix before model input [OK]

Common Mistakes:

• Ignoring pre-trained vectors and training from scratch
• Using word indices without embeddings
• Applying embeddings only at output layer