BERT pre-training concept in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does BERT stand for in NLP?

BERT stands for Bidirectional Encoder Representations from Transformers. It is a model designed to understand the context of words in both directions in a sentence.

beginner

What are the two main tasks used in BERT pre-training?

The two main tasks are:
1. Masked Language Modeling (MLM): Randomly hides some words and trains the model to predict them.
2. Next Sentence Prediction (NSP): Trains the model to understand if one sentence logically follows another.

intermediate

Why is BERT called 'bidirectional'?

Because BERT looks at the words before and after a target word at the same time during training. This helps it understand the full context, unlike older models that read text only left-to-right or right-to-left.

beginner

Explain Masked Language Modeling (MLM) in simple terms.

MLM is like a fill-in-the-blank game. Some words in a sentence are hidden, and BERT tries to guess those missing words using the surrounding words. This helps BERT learn word meanings and context.

intermediate

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

NSP teaches BERT to understand relationships between sentences. It learns to predict if one sentence naturally follows another, which helps in tasks like question answering and text summarization.

What does BERT use to understand the context of words?

A Bidirectional reading of sentences

B Only left-to-right reading

C Only right-to-left reading

D Random word order

BERT reads sentences in both directions to understand full context.

In Masked Language Modeling, what does BERT try to predict?

A The topic of the text

B The next sentence

C Hidden words in a sentence

D The length of the sentence

MLM hides some words and BERT predicts those missing words.

What is the goal of Next Sentence Prediction in BERT?

A Predict the next word in a sentence

B Predict if one sentence follows another

C Predict the sentiment of a sentence

D Predict the length of a paragraph

NSP helps BERT learn if one sentence logically follows another.

Why is BERT pre-trained before fine-tuning on specific tasks?

A To avoid training

B To memorize answers

C To reduce model size

D To learn general language understanding

Pre-training helps BERT learn language patterns useful for many tasks.

Which architecture does BERT use?

A Transformer Encoder

B Convolutional Neural Network

C Support Vector Machine

D Recurrent Neural Network

BERT is based on the Transformer encoder architecture.

Describe the two main pre-training tasks of BERT and why they are important.

Think about how BERT learns words and sentence order.

Explain why BERT's bidirectional approach helps it understand language better than previous models.

Consider how knowing words before and after helps guess meaning.

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