Tokenization and vocabulary in Prompt Engineering / GenAI - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is tokenization in natural language processing?

Tokenization is the process of breaking text into smaller pieces called tokens, such as words or subwords, to help machines understand and work with language.

beginner

Why do we need a vocabulary in language models?

A vocabulary is a list of all tokens the model knows. It helps the model convert text into numbers it can process and generate text by choosing tokens from this list.

intermediate

What is the difference between word-level and subword-level tokenization?

Word-level tokenization splits text into whole words, while subword-level breaks words into smaller parts. Subword tokenization helps handle rare or new words better.

intermediate

How does tokenization affect the size of the vocabulary?

Finer tokenization (like subwords) creates a smaller vocabulary because it reuses parts of words, while word-level tokenization needs a bigger vocabulary to cover all words.

beginner

What happens if a token is not in the vocabulary during model use?

If a token is missing, the model usually replaces it with a special unknown token or breaks it into smaller known tokens to still understand it.

What is the main goal of tokenization?

A To remove punctuation from text

B To translate text into another language

C To compress text into fewer characters

D To split text into smaller pieces called tokens

Tokenization breaks text into tokens so machines can process language.

Which tokenization method helps handle new or rare words better?

A Subword-level tokenization

B Word-level tokenization

C Character-level tokenization

D Sentence-level tokenization

Subword tokenization breaks words into smaller parts, helping with rare or new words.

What does a vocabulary in a language model contain?

A All possible sentences

B All tokens the model can recognize

C All grammar rules

D All training data

Vocabulary lists all tokens the model knows to convert text into numbers.

What is a common way models handle tokens not in their vocabulary?

A Ignore the token completely

B Add the token to the vocabulary instantly

C Replace with an unknown token or split into smaller tokens

D Translate the token to another language

Models replace unknown tokens or break them into smaller known tokens to understand them.

Which tokenization approach usually results in the largest vocabulary?

A Word-level tokenization

B Subword-level tokenization

C Character-level tokenization

D Sentence-level tokenization

Word-level tokenization needs a large vocabulary to cover all words.

Explain in your own words what tokenization is and why it is important for language models.

Think about how you might split a sentence into pieces to help a computer read it.

Describe the role of vocabulary in a language model and what happens when the model encounters a token not in its vocabulary.

Consider how a dictionary helps you understand words, and what you do if a word is missing.