N-gram

A contiguous sequence of n items (typically words) from a text, used in language modeling to predict the probability of a word based on its predecessors. A unigram considers single words in isolation, a bigram considers pairs of consecutive words, and a trigram considers sequences of three. In AAC word prediction, n-gram models estimate which words are most likely to follow the user's input by analyzing patterns learned from training text. Higher-order n-grams capture more context but require more training data.