A neural network approach to selectional preference acquisition

Abstract : This paper investigates the use of neural networks for the acquisition of selectional preferences. Inspired by recent advances of neural network models for NLP applications, we propose a neural network modelthat learns to discriminate between felicitous and infelicitous arguments for a particular predicate. The model is entirely unsupervised preferences are learned fromunannotated corpus data. We propose twoneural network architectures: one that handles standard two-way selectional prefer-ences and one that is able to deal with multi-way selectional preferences. Themodel’s performance is evaluated on a pseudo-disambiguation task, on which it is shown to achieve state of the art performance.