Verb Subcategorization Kernels for Automatic Semantic Labeling

Recently, many researches in natural language learning have considered the representation of complex linguistic phenomena by means of structural kernels. In particular, tree kernels have been used to represent verbal subcategorization frame (SCF) information for predicate argument classification. As the SCF is a relevant clue to learn the relation between syntax and semantic, the classification algorithm accuracy was remarkable enhanced. In this article, we extend such work by studying the impact of the SCF tree kernel on both PropBank and FrameNet semantic roles. The experiments with Support Vector Machines (SVMs) confirm a strong link between the SCF and the semantics of the verbal predicates as well as the benefit of using kernels in diverse and complex test conditions, e.g. classification of unseen verbs.