Natural Language Processing · Level 2 of 5
N-Gram
A contiguous sequence of n units used as a feature or language-model context.
The units can be tokens or characters.
Example
A bigram model considers pairs of neighboring words.
Listen to the definition and example
Audio transcript
N-Gram. A contiguous sequence of n units used as a feature or language-model context. The units can be tokens or characters. For example: A bigram model considers pairs of neighboring words.
Explore this concept
Why it matters
This helps you understand how language becomes data and where processing can lose meaning.
Start with
Related concepts
Quick recall question
Try answering before looking back at the definition.