BERT pre-training concept in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the BERT tokenizer from the transformers library.

NLP

from transformers import [1]

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

ABertModel

BBertTokenizer

CAutoModel

DGPT2Tokenizer

Attempts:

3 left

💡 Hint

Common Mistakes

Importing the model class instead of the tokenizer.

Using a tokenizer from a different model like GPT-2.

The BERT tokenizer is imported using BertTokenizer from the transformers library.

2fill in blank

medium

Complete the code to create a masked language modeling label tensor where tokens to predict are marked with their IDs and others with -100.

NLP

labels = input_ids.clone()
labels[~masked_indices] = [1]

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

Ainput_ids

BNone

C0

D-100

Attempts:

3 left

💡 Hint

Common Mistakes

Setting unmasked tokens to 0 which is a valid token ID.

Leaving unmasked tokens unchanged.

In BERT pre-training, tokens not masked are set to -100 in labels to ignore them during loss calculation.

3fill in blank

hard

Fix the error in the code that creates the attention mask for BERT input tokens.

NLP

attention_mask = (input_ids != [1]).long()

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

A0

B1

C-100

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Using 1 as the padding token ID.

Using None which causes errors.

The attention mask marks padding tokens (usually 0) as 0 and real tokens as 1.

4fill in blank

hard

Fill both blanks to create a dictionary for masked language modeling inputs and labels.

NLP

inputs = {
    'input_ids': [1],
    'labels': [2]
}

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

Ainput_ids

Blabels

Cattention_mask

Dtoken_type_ids

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing attention_mask or token_type_ids as labels.

Swapping input_ids and labels.

The inputs dictionary for BERT MLM includes input_ids and labels for training.

5fill in blank

hard

Fill the blank to compute the masked language modeling loss using the model outputs and labels.

NLP

from torch.nn import CrossEntropyLoss

loss_fct = CrossEntropyLoss()
logits = outputs.logits
masked_lm_loss = loss_fct(logits.view(-1, logits.size([1])), labels.view(-1))

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

A2

B0

C3

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong dimension index causing shape mismatch.

Not reshaping logits and labels properly.

The logits tensor shape is (batch_size, sequence_length, vocab_size), so dimension 2 is vocab size for loss calculation.

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