Functional Distributional Semantics
This work addresses challenges in distributional semantics for natural language processing, offering a new approach that integrates formal semantics with machine learning techniques.
The paper tackles the limitations of vector space models in capturing semantic phenomena by proposing a novel probabilistic framework that separates predicates from entities and uses Bayesian inference based on logical forms, demonstrating feasibility through training on a parsed corpus and evaluation on similarity datasets.
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.