We propose CMSMs, a novel type of generic compositional models for syntactic and semantic aspects of natural language, based on matrix multiplication. We argue for the structural ...
We develop the syntactic topic model (STM), a nonparametric Bayesian model of parsed documents. The STM generates words that are both thematically and syntactically constrained, w...
In data-oriented language processing, an annotated language corpus is used as a stochastic grammar. The most probable analysis of a new sentence is constructed by combining fragme...
Grishin ([10]) proposed enriching the Lambek calculus with multiplicative disjunction (par) and coresiduals. Applications to linguistics were discussed by Moortgat ([15]), who spok...
This paper introduces and analyzes a battery of inference models for the problem of semantic role labeling: one based on constraint satisfaction, and several strategies that model...