N-Gram Counter
N-Gram Counter finds recurring sequences of adjacent words in text, from pairs through five-word phrases.
Example: n-gram counter
a b a b
a b 2
How to use this tool
- Paste enough text to contain repeated phrases.
- Choose a sequence length from two to five words.
- Review counts and inspect the original sentence before acting.
What an n-gram is
An n-gram is a run of adjacent tokens. With a two-word setting, “quick brown fox” contains “quick brown” and “brown fox”; a three-word setting contains “quick brown fox.” The tool uses its word tokenizer, lowercases the tokens for grouping, and counts each sliding window. It does not require a phrase to start at a sentence boundary.
When phrase counts help
Repeated two-word combinations can expose stock wording or inconsistent terminology in a long draft. Longer combinations can reveal near-duplicated instructions, boilerplate, or a phrase overused in headings. Use the counts to locate candidates, then read surrounding text; some repetition is useful for clarity.
Choose the right comparison
Word Frequency Counter counts individual words, not sequences. Text Diff Checker compares two texts line by line and is better for finding changes between versions. N-gram counts do not identify intent, synonyms, or whether a repeated phrase is a problem.
Questions people ask
Can I count six-word phrases?
No; this tool supports sequence lengths two through five.
Does word order matter?
Yes; “red blue” and “blue red” are different sequences.
Are phrases normalized for case?
Yes; the tokenizer’s words are lowercased before grouping.