Skip to content
uencoder

N-gram

An N-gram is a sequence of N consecutive units (characters or words) segmented from text, used in language models, similarity, and text analysis.

Purpose

Decomposes text into fixed-length segments, making statistics and comparison easier.

Mechanism

Slide a window of size N with step 1 over characters or words. For example, the character 2-grams of "hello" are he, el, ll, lo. Used in N-gram language models (predicting the probability of the next unit) and Jaccard/Dice similarity.

Use cases

  • N-gram language models
  • Spelling correction (character n-gram similarity)
  • Text classification and language detection
  • Keyword extraction

Examples

  • Input 
    "hello" 2-grams
    Output 
    he, el, ll, lo

    Character bigrams

Common errors

Too-large N causes sparsity and overfitting
Choose N based on corpus size (usually 2-3)

Related terms

Tokenization
Tokenization splits text into a sequence of semantic units (words, subwords, characters); it is a foundational step in NLP and search engines.
GLOSSARY
TF-IDF
TF-IDF (term frequency-inverse document frequency) measures how important a word is to a document: words frequent in the document but rare in the corpus receive high weights.
GLOSSARY
Cosine Similarity
Cosine similarity measures the cosine of the angle between two vectors, ignoring vector length; it is widely used for text-vector similarity computation.
GLOSSARY

References