The factored language model (FLM) is an extension of a conventional language model. In an FLM, each word is viewed as a vector of k factors: An FLM provides the probabilistic model where the prediction of a factor is based on parents . For example, if represents a word token and represents a Part of speech tag for English, the expression gives a model for predicting current word token based on a traditional Ngram model as well as the Part of speech tag of the previous word.
A major advantage of factored language models is that they allow users to specify linguistic knowledge such as the relationship between word tokens and Part of speech in English, or morphological information (stems, root, etc.) in Arabic.
Like N-gram models, smoothing techniques are necessary in parameter estimation. In particular, generalized back-off is used in training an FLM.
Famous quotes containing the words language and/or model:
“Never resist a sentence you like, in which language takes its own pleasure and in which, after having abused it for so long, you are stupefied by its innocence.”
—Jean Baudrillard (b. 1929)
“The striking point about our model family is not simply the compete-compete, consume-consume style of life it urges us to follow.... The striking point, in the face of all the propaganda, is how few Americans actually live this way.”
—Louise Kapp Howe (b. 1934)