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:
“The human face is the organic seat of beauty.... It is the register of value in development, a record of Experience, whose legitimate office is to perfect the life, a legible language to those who will study it, of the majestic mistress, the soul.”
—Eliza Farnham (1815–1864)
“I had a wonderful job. I worked for a big model agency in Manhattan.... When I got on the subway to go to work, it was like traveling into another world. Oh, the shops were beautiful, we had Bergdorf’s, Bendel’s, Bonwit’s, DePinna. The women wore hats and gloves. Another world. At home, it was cooking, cleaning, taking care of the kids, going to PTA, Girl Scouts. But when I got into the office, everything was different, I was different.”
—Estelle Shuster (b. c. 1923)