Learning Semantics and Selectional Preference of Adjective-Noun Pairs.

We investigate the semantic relationship between a noun and its adjectival modifiers. We introduce a class of probabilistic models that enable us to to simultaneously capture both the semantic similarity of nouns and modifiers, and adjective-noun selectional preference. Through a combination of novel and existing evaluations we test the degree to which adjective-noun relationships can be categorised. We analyse the effect of lexical context on these relationships, and the efficacy of the latent semantic representation for disambiguating word meaning.