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:
“It’s not that we want the political jobs themselves ... but they seem to be the only language the men understand. We don’t really want these $200 a year jobs. But the average man doesn’t understand working for a cause.”
—Jennie Carolyn Van Ness (b. c. 1890–?)
“Research shows clearly that parents who have modeled nurturant, reassuring responses to infants’ fears and distress by soothing words and stroking gentleness have toddlers who already can stroke a crying child’s hair. Toddlers whose special adults model kindliness will even pick up a cookie dropped from a peer’s high chair and return it to the crying peer rather than eat it themselves!”
—Alice Sterling Honig (20th century)