Modeling Meaning a Kantian Intervention in Vector Space Semantics

Abstract

This thesis discusses the implementation of a set of logical forms to enrich the way meaning is modeled in a vector-based system of conceptual memory. Vector-space models can account for a variety of psycho-linguistic phenomena by representing relationships between concepts as distance in a high-dimensional space. But they lack logical organizational structure without which inferential operations are impossible. Augmenting cognitive architectures with innate, logical structures might be the key to resolving this issue. But proposing such structures risks over-attributing the complexity of behavior to complexity in the architecture. I propose using Kant's critical work for a strong theory to select a minimal set of logical forms. The Kantian logical forms are implemented onto vector space architecture in a system (Kantian-HDM) created in R programming language and has been published on GitHub. The results of the simulations run in the system are presented along with a description of the inferential behavior exhibited.ii Acknowledgment First and foremost, I would like to thank my co-supervisors Andrew Brook and Robert West. Without Andrew's brilliant course on Kant, I would never have been able to give this work the philosophical direction vital to it. The many discussions I had with Rob were crucially important to stay motivated as I navigated the highly intersectional domain of this work. Their support in preparation and writing of this thesis was critical for its success. Second, I am grateful to Raj Singh for introducing me to the domain of computational linguistics and providing key feedback for this work. Thirdly, I want to extend my gratitude to Mathew Kelly who made himself available to help me through the often obscure literature and models on the topic of this thesis.