Towards Compositional Tree Kernels

Distributional Compositional Semantics (DCS) methods combine lexical vectors according to algebraic operators or functions to model the meaning of complex linguistic phrases. On the other hand, several textual inference tasks rely on supervised kernel-based learning, whereas Tree Kernels (TK) have been shown suitable to the modeling of syntactic and semantic similarity between linguistic instances. While the modeling of DCS for complex phrases is still an open research issue, TKs do not account for compositionality. In this paper, a novel kernel called Compositionally Smoothed Partial Tree Kernel is proposed integrating DCS operators into the TK estimation. Empirical results over Semantic Text Similarity and Question Classification tasks show the contribution of semantic compositions with respect to tradi-