bigram

This term is primarily used in the technical domains of computational linguistics, cryptography, and statistics. It describes a specific type of n-gram where n equals two, focusing on the statistical relationship between a pair of consecutive items. While it can refer to pairs of characters, it most frequently refers to pairs of words in the context of language modeling.

In practical application, bigrams are used to predict the next word in a sequence based on the current word, forming the basis for early autocomplete systems and spell-checkers. It is a neutral, descriptive term with no emotional connotation, used almost exclusively in academic or professional technical discourse.