BERT tokenization (WordPiece) in NLP

Introduction

BERT tokenization breaks text into smaller pieces called tokens. This helps the model understand words and parts of words better.

When preparing text data for BERT-based models.

When you want to handle unknown or rare words by splitting them into known parts.

When you need consistent tokenization that matches BERT's training.

When working with tasks like text classification, question answering, or named entity recognition using BERT.

Syntax

NLP

from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
tokens = tokenizer.tokenize(text)
ids = tokenizer.convert_tokens_to_ids(tokens)

tokenize(text) splits the input text into WordPiece tokens.

convert_tokens_to_ids(tokens) converts tokens into numbers BERT understands.

Examples

This splits 'playing' into ['play', '##ing'] showing WordPiece splits suffixes.

NLP

text = "playing"
tokens = tokenizer.tokenize(text)
print(tokens)

Unknown words get split into known pieces like ['un', '##aff', '##able'].

NLP

text = "unaffable"
tokens = tokenizer.tokenize(text)
print(tokens)

Simple words stay whole: ['hello', 'world'].

NLP

text = "hello world"
tokens = tokenizer.tokenize(text)
print(tokens)

Sample Model

This code shows how to split text into WordPiece tokens, convert them to IDs, and decode back to text using BERT tokenizer.

NLP

from transformers import BertTokenizer

# Load BERT tokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

# Sample text
text = "Playing with BERT tokenization is fun!"

# Tokenize text
tokens = tokenizer.tokenize(text)
print("Tokens:", tokens)

# Convert tokens to IDs
token_ids = tokenizer.convert_tokens_to_ids(tokens)
print("Token IDs:", token_ids)

# Decode back to text
decoded_text = tokenizer.decode(token_ids)
print("Decoded text:", decoded_text)

Important Notes

WordPiece tokens starting with '##' mean they are parts of a word, not standalone.

BERT tokenizer lowercases text by default for 'bert-base-uncased'.

Token IDs are what BERT uses internally to understand text.

Summary

BERT tokenization splits words into smaller pieces called WordPieces.

This helps handle unknown words by breaking them into known parts.

Use BERT tokenizer to prepare text for BERT models correctly.

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