Composition of Compound Nouns Using Distributional Semantics

The use of distributional semantics to represent the meaning of a single word has proven to be very effective, but there still is difficulty representing the meaning of larger constituents, such as a noun phrase. In general, it is unclear how to find a representation of phrases that preserves syntactic distinctions and the relationship between a compound’s constituents. This paper is an attempt to find the best representation of nominal compounds in Spanish and English, and evaluates the performance of different compositional models by using correlations with human similarity judgments and by using compositional representations as input into an SVM classifying the semantic relation between nouns within a compound. This paper also evaluates the utility of different function’s compositional representations, which give our model a slight advantage in accuracy over other state-of-the-art semantic relation classifiers.