A novel theoretical framework for describing stochastic gram-mars is proposed based on a small set of basic random variables that generate tree structures and relate them to surface strings. A number of prominent statistical language models are formulated as stochastic processes over these basic random variables.
CITATION STYLE
Samuelsson, C. (2000). A theory of stochastic grammars. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 1835, pp. 92–105). Springer Verlag. https://doi.org/10.1007/3-540-45154-4_9
Mendeley helps you to discover research relevant for your work.