Paper: Stochastic Lexicalized Tree-Adjoining Grammars

ACL ID C92-2066
Title Stochastic Lexicalized Tree-Adjoining Grammars
Venue International Conference on Computational Linguistics
Session Main Conference
Year 1992
  • Yves Schabes (University of Pennsylvania, Philadelphia PA)

The notion of stochastic lexicalized tree-adjoining grammar (SLTAG) is formally defined. The parameters of a SLTAG correspond to the probability of combining two structures each one associated with a word. The characteristics of SLTAG are unique and novel since it is lexieally sensitive (as N-gram models or Hidden Markov Models) and yet hierarchical (as stochastic context-free grammars). Then, two basic algorithms for SLTAG arc intro- duced: an algorithm for computing the probability of a sentence generated by a SLTAG and an inside-outside- like iterative algorithm for estimating the parameters of a SLTAG given a training corpus. Finally, we should how SLTAG enables to define a lexicalized version of stochastic context-free grammars and we report preliminary experiments showing some of the...