Functional Distributional Semantics

TL;DR

This paper introduces a probabilistic framework for distributional semantics that combines formal semantics with machine learning, enabling Bayesian inference on logical forms using neural networks and RBMs.

Contribution

It presents a novel approach that separates predicates from entities, integrating formal semantics with probabilistic models for improved semantic understanding.

Findings

Feasible implementation with RBMs and neural networks.

Effective training on parsed corpus.

Competitive performance on similarity datasets.

Abstract

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.