CDSMs for Semantic Relatedness and Entailment

Distributional Semantics Models (DSMs) have become widely accepted as successful models for lexical semantics. However their extension to handling larger structural units such as entire sentences remains challenging. Compositional DSMs (CDSMs) aim to successfully model sentence semantics by taking into account grammatical structure and logical words, which are ignored by simpler models. We explore a recursive matrix-vector space model, where each word or phrase has associated with it a vector capturing its semantics, as well as a matrix capturing how it alters the meanings of other words or phrases in its vicinity. We proceed to test this proposed CDSM on the tasks of semantic relatedness score prediction and semantic entailment classification, over the SICK data set of approximately 10,000 sentence pairs.