Which representation yields a numeric vector by counting word frequency across a document?

Which representation yields a numeric vector by counting word frequency across a document?

• A. Term Frequency (TF)
• B. Bag of Words
• C. Count Bag of Words
• D. Dictionary (Heuristic)

Answer: (C)

Counting word occurrences across a document creates a numeric vector by mapping each word in a fixed vocabulary to how many times it appears in that document. For every term in the vocabulary, you tally its frequency in the document, and the resulting vector has one entry per term, equal to that term’s count. This explicit counting defines the Count Bag of Words representation, giving raw counts as features. In contrast, applying term frequency usually normalizes those counts (to proportions or frequencies), so you don’t get pure counts. A dictionary or heuristic approach isn’t about tallying word occurrences in a document, and while Bag of Words is related, the count-based form specifically yields a numeric vector of raw frequencies.

Counting word occurrences across a document creates a numeric vector by mapping each word in a fixed vocabulary to how many times it appears in that document. For every term in the vocabulary, you tally its frequency in the document, and the resulting vector has one entry per term, equal to that term’s count. This explicit counting defines the Count Bag of Words representation, giving raw counts as features. In contrast, applying term frequency usually normalizes those counts (to proportions or frequencies), so you don’t get pure counts. A dictionary or heuristic approach isn’t about tallying word occurrences in a document, and while Bag of Words is related, the count-based form specifically yields a numeric vector of raw frequencies.