2016/06/26 by Guy Emerson, Emerson, Guy, Ann Copestake +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.CL
paper · pdf · doi:10.48550/arxiv.1606.08003
Published at Representation Learning for NLP workshop at ACL 2016, https://sites.google.com/site/repl4nlp2016/
arxiv created 2016/06/26 · arxiv updated 2016/06/28
Vector space models have become popular in distributional semantics, despite the challenges they face in capturing various semantic phenomena. We propose a novel probabilistic framework which draws on both formal semantics and recent advances in machine learning. In particular, we separate predicates from the entities they refer to, allowing us to perform Bayesian inference based on logical forms. We describe an implementation of this framework using a combination of Restricted Boltzmann Machines and feedforward neural networks. Finally, we demonstrate the feasibility of this approach by training it on a parsed corpus and evaluating it on established similarity datasets.