Category-Theoretic Quantitative Compositional Distributional Models of Natural Language Semantics

Abstract

This thesis is about the problem of compositionality in distributional semantics. Distributional semantics presupposes that the meanings of words are a function of their occurrences in textual contexts. It models words as distributions over these contexts and represents them as vectors in high dimensional spaces. The problem of compositionality for such models concerns itself with how to produce representations for larger units of text by composing the representations of smaller units of text. This thesis focuses on a particular approach to this compositionality problem, namely using the categorical framework developed by Coecke, Sadrzadeh, and Clark, which combines syntactic analysis formalisms with distributional semantic representations of meaning to produce syntactically motivated composition operations. This thesis shows how this approach can be theoretically extended and practically implemented to produce concrete compositional distributional models of natural language semantics. It furthermore demonstrates that such models can perform on par with, or better than, other competing approaches in the field of natural language processing. There are three principal contributions to computational linguistics in this thesis. The first is to extend the DisCoCat framework on the syntactic front and semantic front, incorporating a number of syntactic analysis formalisms and providing learning procedures allowing for the generation of concrete compositional distributional models. The second contribution is to evaluate the models developed from the procedures presented here, showing that they outperform other compositional distributional models present in the literature. The third contribution is to show how using category theory to solve linguistic problems forms a sound basis for research, illustrated by examples of work on this topic, that also suggest directions for future research.

DPhil Thesis, University of Oxford, Submitted and accepted in 2013

References in corpus (6)

• From Frequency to Meaning: Vector Space Models of Semantics
• Experimental Support for a Categorical Compositional Distributional Model of Meaning
• Lambek vs. Lambek: Functorial Vector Space Semantics and String Diagrams for Lambek Calculus
• Towards a Formal Distributional Semantics: Simulating Logical Calculi with Tensors
• Experimenting with Transitive Verbs in a DisCoCat
• Categories for the practising physicist

Cited by in corpus (8)

• A Convolutional Neural Network for Modelling Sentences
• Quantum Algorithms for Compositional Natural Language Processing
• A CCG-Based Version of the DisCoCat Framework
• Distributed Representations for Compositional Semantics
• Investigating the Role of Prior Disambiguation in Deep-learning Compositional Models of Meaning
• Learning Semantically and Additively Compositional Distributional Representations
• Learning Type-Driven Tensor-Based Meaning Representations
• The Abstract Structure of Quantum Algorithms