BERT pre-training concept in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main goal of BERT's Masked Language Model (MLM) during pre-training?

BERT uses a special pre-training task called Masked Language Model (MLM). What is the main goal of MLM?

A Predict randomly masked words in a sentence using context from both sides

B Classify the sentiment of a sentence as positive or negative

C Predict the next word in a sentence given all previous words

D Translate a sentence from one language to another

💡 Hint

Think about how BERT learns from words hidden in the middle of sentences.

MLM trains BERT to predict missing words by looking at words before and after the masked word, helping it understand context deeply.

🧠 Conceptual

intermediate

What is the purpose of the Next Sentence Prediction (NSP) task in BERT pre-training?

Besides MLM, BERT uses Next Sentence Prediction (NSP) during pre-training. What does NSP help BERT learn?

A To predict the sentiment of a sentence

B To determine if one sentence logically follows another

C To translate sentences between languages

D To generate new sentences from scratch

💡 Hint

Think about how BERT understands relationships between two sentences.

NSP trains BERT to decide if a second sentence naturally follows the first, helping it learn sentence relationships useful for tasks like question answering.

❓ Model Choice

advanced

Which architecture component enables BERT to use context from both left and right sides during MLM pre-training?

BERT can look at words before and after a masked word simultaneously. Which part of BERT's architecture allows this?

A Unidirectional LSTM layers

B Recurrent neural networks with attention

C Convolutional neural networks

D Bidirectional Transformer encoder layers

💡 Hint

Think about which architecture processes all words at once with attention.

BERT uses Transformer encoder layers that attend to all words in the input simultaneously, enabling bidirectional context understanding.

❓ Metrics

advanced

During BERT pre-training, which metric best indicates how well the model predicts masked tokens?

Which metric is commonly used to measure BERT's performance on the Masked Language Model task during pre-training?

A Mean squared error of token embeddings

B BLEU score for sentence generation

C Accuracy of predicting masked tokens

D F1 score for next sentence prediction

💡 Hint

Focus on how well the model guesses the hidden words correctly.

Accuracy measures the percentage of masked tokens correctly predicted, directly reflecting MLM task performance.

🔧 Debug

expert

What error will occur if BERT's input tokens are not properly masked during MLM pre-training?

Suppose you accidentally feed BERT input sequences without masking any tokens during MLM pre-training. What is the most likely outcome?

A The loss will be very low but the model won't learn to predict masked words

B The model will train normally with no issues

C A runtime error will occur due to missing mask tokens

D The model will overfit quickly and produce random predictions

💡 Hint

Think about what happens if the model never has to guess missing words.

If no tokens are masked, the model always sees the full input and does not learn to predict missing words, resulting in low loss but poor MLM learning.

Practice

1. What are the two main tasks used during BERT pre-training?

easy

A. Text Classification and Named Entity Recognition

B. Masked Language Model and Next Sentence Prediction

C. Part-of-Speech Tagging and Dependency Parsing

D. Sentiment Analysis and Machine Translation

Solution

1. Step 1: Understand BERT pre-training tasks

   BERT is trained to predict missing words and the order of sentences, which correspond to Masked Language Model (MLM) and Next Sentence Prediction (NSP).

2. Step 2: Match tasks to options

   Only Masked Language Model and Next Sentence Prediction lists MLM and NSP, the two key pre-training tasks of BERT.

3. Final Answer:

   Masked Language Model and Next Sentence Prediction -> Option B

4. Quick Check:

   BERT pre-training tasks = MLM + NSP [OK]

Hint: Remember BERT guesses missing words and sentence order [OK]

Common Mistakes:

• Confusing fine-tuning tasks with pre-training tasks
• Mixing up NLP tasks unrelated to BERT pre-training
• Thinking BERT uses only one pre-training task

2. Which of the following is the correct way to describe the Masked Language Model (MLM) task in BERT pre-training?

easy

A. Predict randomly masked words in a sentence

B. Predict the next sentence given the current sentence

C. Classify the sentiment of a sentence

D. Translate a sentence to another language

Solution

1. Step 1: Define Masked Language Model (MLM)

   MLM involves randomly masking some words in a sentence and training the model to predict those masked words.

2. Step 2: Match definition to options

   Predict randomly masked words in a sentence correctly describes MLM as predicting masked words, while others describe different tasks.

3. Final Answer:

   Predict randomly masked words in a sentence -> Option A

4. Quick Check:

   MLM = predict masked words [OK]

Hint: MLM means guessing hidden words in sentences [OK]

Common Mistakes:

• Confusing MLM with Next Sentence Prediction
• Thinking MLM predicts entire sentences
• Mixing MLM with classification tasks

3. Consider the following simplified code snippet for BERT pre-training MLM task:

sentence = ['The', 'cat', 'sat', 'on', 'the', 'mat']
masked_sentence = ['The', '[MASK]', 'sat', 'on', 'the', 'mat']
predicted_word = model.predict(masked_sentence)
print(predicted_word)

If the model works correctly, what should predicted_word be?

medium

A. 'cat'

B. 'mat'

C. 'dog'

D. 'sat'

Solution

1. Step 1: Identify the masked word in the sentence

   The original sentence is ['The', 'cat', 'sat', 'on', 'the', 'mat'], and the masked sentence replaces 'cat' with '[MASK]'.

2. Step 2: Predict the masked word

   The model should predict the missing word 'cat' to correctly fill the mask.

3. Final Answer:

   'cat' -> Option A

4. Quick Check:

   Masked word prediction = 'cat' [OK]

Hint: Masked word is replaced by [MASK], predict original word [OK]

Common Mistakes:

• Choosing a word from the sentence but not the masked one
• Confusing masked word with next sentence prediction
• Assuming model predicts random words

4. In BERT pre-training, a common error is mixing up the Next Sentence Prediction (NSP) task. Which of the following statements is a mistake in NSP implementation?

medium

A. Feeding two sentences and predicting if the second follows the first

B. Randomly pairing sentences for negative examples

C. Using a binary classifier to decide sentence order

D. Predicting masked words inside a single sentence

Solution

1. Step 1: Understand NSP task

   NSP involves feeding two sentences and predicting if the second sentence logically follows the first.

2. Step 2: Identify incorrect statement

   Predicting masked words inside a single sentence describes predicting masked words, which is MLM, not NSP, so it is a mistake in NSP implementation.

3. Final Answer:

   Predicting masked words inside a single sentence -> Option D

4. Quick Check:

   NSP ≠ masked word prediction [OK]

Hint: NSP predicts sentence order, not masked words [OK]

Common Mistakes:

• Confusing NSP with MLM
• Not using sentence pairs for NSP
• Skipping negative examples in NSP

5. You want to improve BERT's understanding of sentence relationships by modifying the Next Sentence Prediction (NSP) task. Which approach would best enhance NSP during pre-training?

hard

A. Increase the percentage of masked words in MLM to 50%

B. Replace NSP with a sentiment classification task

C. Add more negative sentence pairs that are unrelated

D. Train only on single sentences without pairs

Solution

1. Step 1: Understand NSP goal

   NSP aims to teach the model to distinguish if one sentence follows another logically by using positive and negative sentence pairs.

2. Step 2: Choose best enhancement

   Adding more negative sentence pairs (unrelated sentences) improves the model's ability to learn sentence relationships, enhancing NSP.

3. Final Answer:

   Add more negative sentence pairs that are unrelated -> Option C

4. Quick Check:

   More negative pairs = better NSP learning [OK]

Hint: More unrelated sentence pairs improve NSP task [OK]

Common Mistakes:

• Confusing MLM changes with NSP improvements
• Removing sentence pairs breaks NSP
• Replacing NSP with unrelated tasks