BERT tokenization (WordPiece) in NLP - Model Pipeline Trace

Model Pipeline - BERT tokenization (WordPiece)

This pipeline shows how BERT breaks text into smaller pieces called WordPieces. It helps the model understand words, even if they are new or rare.

Data Flow - 4 Stages

1Raw Text Input

1 sentence (string)→Input sentence as plain text→1 sentence (string)

"Playing football is fun!"

↓

2Basic Tokenization

1 sentence (string)→Split sentence into words and punctuation→List of tokens (words and punctuation)

["Playing", "football", "is", "fun", "!"]

↓

3WordPiece Tokenization

List of tokens→Break words into subword pieces using WordPiece vocabulary→List of WordPiece tokens

["Play", "##ing", "football", "is", "fun", "!"]

↓

4Convert Tokens to IDs

List of WordPiece tokens→Map each token to a unique number from vocabulary→List of token IDs (integers)

[1234, 567, 4321, 29, 876, 17]

Training Trace - Epoch by Epoch

Loss
0.9 |****
0.8 |*** 
0.7 |**  
0.6 |**  
0.5 |*   
0.4 |*   
0.3 |    
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.60	Model starts learning basic token patterns.
2	0.65	0.72	Loss decreases as model learns subword relationships.
3	0.50	0.80	Model improves understanding of word pieces.
4	0.40	0.85	Training converges with better token predictions.
5	0.35	0.88	Final epoch shows stable loss and high accuracy.

Prediction Trace - 4 Layers

Layer 1: Input Sentence

Layer 2: Basic Tokenization

Layer 3: WordPiece Tokenization

Layer 4: Convert Tokens to IDs

Model Quiz - 3 Questions

What does the '##' symbol mean in WordPiece tokens?

A It marks the start of a new word.

B It indicates punctuation.

C It shows the token is a continuation of the previous word piece.

D It means the token is a stop word.

Key Insight

BERT's WordPiece tokenization helps the model understand words by breaking them into smaller parts. This allows it to handle new or rare words better, improving language understanding.

Practice

1. What is the main purpose of BERT's WordPiece tokenization?

easy

A. To split words into smaller known pieces for better handling of unknown words

B. To translate text into another language

C. To remove stop words from sentences

D. To convert text into numerical vectors directly

Solution

1. Step 1: Understand WordPiece tokenization

   WordPiece breaks words into smaller parts called tokens, especially for unknown or rare words.

2. Step 2: Identify the purpose of this splitting

   This splitting helps the model recognize parts of words it has seen before, improving understanding.

3. Final Answer:

   To split words into smaller known pieces for better handling of unknown words -> Option A

4. Quick Check:

   WordPiece = splitting unknown words [OK]

Hint: WordPiece breaks unknown words into known parts [OK]

Common Mistakes:

• Thinking WordPiece translates text
• Confusing tokenization with stop word removal
• Assuming WordPiece directly converts text to numbers

2. Which of the following is the correct way to represent the word 'unaffable' using WordPiece tokens?

easy

A. ["un", "##affable"]

B. ["unaffable"]

C. ["un", "aff", "able"]

D. ["un", "##aff", "##able"]

Solution

1. Step 1: Understand WordPiece token format

   WordPiece uses '##' to mark tokens that continue from a previous token.

2. Step 2: Analyze the options

   ["un", "##aff", "##able"] correctly splits 'unaffable' into 'un' + '##aff' + '##able', showing continuation tokens.

3. Final Answer:

   ["un", "##aff", "##able"] -> Option D

4. Quick Check:

   Continuation tokens start with ## [OK]

Hint: Look for '##' prefix on continuation tokens [OK]

Common Mistakes:

• Ignoring '##' prefix for continuation tokens
• Treating whole word as one token always
• Splitting tokens without '##' where needed

3. Given the sentence "Playing football is fun", which is the correct WordPiece tokenization output?

medium

A. ["Play", "##ing", "football", "is", "fun"]

B. ["Playing", "football", "is", "fun"]

C. ["Play", "##ing", "foot", "##ball", "is", "fun"]

D. ["Play", "ing", "foot", "##ball", "is", "fun"]

Solution

1. Step 1: Tokenize 'Playing'

   WordPiece splits 'Playing' into 'Play' and '##ing' because 'Play' is a known root.

2. Step 2: Tokenize 'football'

   It splits 'football' into 'foot' and '##ball' as common subwords.

3. Step 3: Check remaining words

   'is' and 'fun' are common words and remain as single tokens.

4. Final Answer:

   ["Play", "##ing", "foot", "##ball", "is", "fun"] -> Option C

5. Quick Check:

   Known roots + ## continuation tokens [OK]

Hint: Split known roots, add ## for continuations [OK]

Common Mistakes:

• Not splitting compound words like football
• Missing ## prefix on continuation tokens
• Treating all words as single tokens

4. Identify the error in this WordPiece tokenization output for the word 'unhappy': ["un", "happy"]

medium

A. Missing '##' prefix on 'happy' token

B. Incorrect splitting; 'unhappy' should be one token

C. Tokens should be reversed order

D. No error; this is correct tokenization

Solution

1. Step 1: Check token continuation rules

   In WordPiece, tokens after the first must start with '##' to show continuation.

2. Step 2: Analyze given tokens

   'happy' is a continuation of 'un', so it should be '##happy', not 'happy'.

3. Final Answer:

   Missing '##' prefix on 'happy' token -> Option A

4. Quick Check:

   Continuation tokens need '##' prefix [OK]

Hint: Check if continuation tokens start with '##' [OK]

Common Mistakes:

• Forgetting '##' on continuation tokens
• Assuming all tokens are standalone
• Thinking order of tokens matters here

5. You want to tokenize the sentence "The unbreakable bond" using BERT's WordPiece tokenizer. Which tokenization output correctly handles the unknown word 'unbreakable'?

hard

A. ["The", "unbreakable", "bond"]

B. ["The", "un", "##break", "##able", "bond"]

C. ["The", "un", "breakable", "bond"]

D. ["The", "un", "##breakable", "bond"]

Solution

1. Step 1: Understand unknown word handling

   WordPiece breaks unknown words into smaller known subwords with '##' for continuation.

2. Step 2: Analyze 'unbreakable'

   It splits into 'un' + '##break' + '##able' to represent parts seen in vocabulary.

3. Step 3: Check other tokens

   'The' and 'bond' are common words and remain as single tokens.

4. Final Answer:

   ["The", "un", "##break", "##able", "bond"] -> Option B

5. Quick Check:

   Unknown words split into known subwords with ## [OK]

Hint: Split unknown words into known parts with ## prefix [OK]

Common Mistakes:

• Treating unknown words as single tokens
• Missing ## on continuation tokens
• Splitting without ## prefix on continuation