LANGUAGE MODELING USING STOCHASTIC CONTEXT-FREE GRAMMARS

Island-driven parsers have interesting potential applications in Autom atic Speech Understanding (ASU). Most of the recently developed ASU sy stems are based on an Acoustic Processor (AP) and a Language Processor (LP). AP computes the a priori probability of the acoustic data given a linguistic interpretation. LP computes the probability of the lingu istic interpretation. This paper describes an effort to adapt island-d riven parsers to handle stochastic context-free grammars. These gramma rs could then be used as Language Models (LM) by LP to compute the pro bability of a linguistic interpretation.