Event Knowledge in Compositional Distributional Semantics

Abstract

The great majority of compositional models in distributional semantics present methods to compose vectors or tensors in a representation of the sentence. Here we propose to enrich one of the best performing methods (vector addition, which we take as a baseline) with distributional knowledge about events. The resulting model is able to outperform our baseline.

Ludovica Pannitto

PhD student in Computational Linguistics

I’m a third year PhD student in Computational Semantics at the CLIC (Language, Interaction and Computation) Laboratory at CIMeC.