Compositional Distributional Cognition

TL;DR

This paper integrates the ICS cognitive architecture with categorical compositional semantics to create a flexible, structure-aware model of cognition that addresses previous limitations and incorporates quantum-inspired tools.

Contribution

It introduces the CatCog framework, combining ICS and CatCo, enabling structured, comparable representations of cognition with enhanced semantic and reasoning capabilities.

Findings

Addresses unbounded representation issues in ICS

Enables comparison of sentences with different structures

Incorporates quantum-inspired tools for reasoning

Abstract

We accommodate the Integrated Connectionist/Symbolic Architecture (ICS) of [32] within the categorical compositional semantics (CatCo) of [13], forming a model of categorical compositional cognition (CatCog). This resolves intrinsic problems with ICS such as the fact that representations inhabit an unbounded space and that sentences with differing tree structures cannot be directly compared. We do so in a way that makes the most of the grammatical structure available, in contrast to strategies like circular convolution. Using the CatCo model also allows us to make use of tools developed for CatCo such as the representation of ambiguity and logical reasoning via density matrices, structural meanings for words such as relative pronouns, and addressing over- and under-extension, all of which are present in cognitive processes. Moreover the CatCog framework is sufficiently flexible to allow for entirely different representations of meaning, such as conceptual spaces. Interestingly, since the CatCo model was largely inspired by categorical quantum mechanics, so is CatCog.