Abstract

The aim of distributional semantics is to design computational techniques that can automatically learn the meanings of words from a body of text. The twin challenges are: how do we represent meaning, and how do we learn these representations? The current state of the art is to represent meanings as vectors—but vectors do not correspond to any traditional notion of meaning. In particular, there is no way to talk about truth, a crucial concept in logic and formal semantics.

In this dissertation, I develop a framework for distributional semantics which answers this challenge. The meanings of words are not represented as vectors, but as functions, which map from entities to probabilities of truth. Such a function can be interpreted both in the machine learning sense of a classifier, and in the formal semantic sense of a truth-conditional function. This simultaneously allows both the use of machine learning techniques to exploit large datasets, and also the use of formal semantic techniques to manipulate the learnt representations. I define a probabilistic graphical model, which incorporates a probabilistic generalisation of model theory (allowing a strong connection with formal semantics), and which generates semantic dependency graphs (allowing it to be trained on a corpus). This graphical model provides a natural way to model logical inference, semantic composition, and context-dependent meanings, where Bayesian inference plays a crucial role. I demonstrate the feasibility of this approach by training a model on WikiWoods, a parsed version of the English Wikipedia, and evaluating it on three tasks. The results indicate that the model can learn information not captured by vector space models.