N-grams in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is an N-gram in natural language processing?

An N-gram is a sequence of N words or tokens that appear together in text. For example, a 2-gram (bigram) is two words in a row, like "good morning."

beginner

What is the difference between a unigram, bigram, and trigram?

A unigram is a single word, a bigram is a pair of two consecutive words, and a trigram is a group of three consecutive words.

intermediate

Why are N-grams useful in language models?

N-grams help predict the next word by looking at the previous N-1 words. This helps computers understand context and improve tasks like text prediction or spelling correction.

intermediate

What is a limitation of using large N in N-grams?

Using large N (like 5-grams or more) can cause data sparsity, meaning many sequences appear rarely or never, making it hard for the model to learn well.

beginner

How can N-grams be used to detect common phrases?

By counting how often N-grams appear in text, we can find common phrases or word combinations that occur frequently, like "New York City" or "machine learning."

What does a bigram represent?

A Two consecutive words

B One single word

C Three consecutive words

D A sentence

A bigram is a sequence of two consecutive words in text.

Which N-gram size is called a trigram?

A 2

B 3

C 1

D 4

A trigram consists of three consecutive words.

What problem can happen if N is too large in N-grams?

A Data sparsity

B Too many common phrases

C Words lose meaning

D Model runs faster

Large N causes data sparsity because many sequences appear rarely, making learning difficult.

How do N-grams help in text prediction?

A By counting characters

B By ignoring previous words

C By translating text

D By looking at previous N-1 words to predict the next

N-grams use the previous N-1 words to predict the next word, helping with text prediction.

Which of these is an example of a unigram?

A "machine learning"

B "learning model"

C "machine"

D "deep neural network"

A unigram is a single word, like "machine."

Explain what N-grams are and how they are used in language processing.

Think about sequences of words and how they help computers understand text.

Describe one advantage and one limitation of using N-grams in text analysis.

Consider what N-grams help with and what problems happen when N grows.