Unified vector space mapping for knowledge representation systems

TL;DR

This paper proposes a unified multidimensional knowledge mapping approach using unsupervised dependency extraction to improve semantic alignment in knowledge representation and AI systems.

Contribution

It introduces a global knowledge map and an adaptive decoder for direct human-system interaction, advancing knowledge representation methods.

Findings

Developed a multidimensional global knowledge map

Proposed an adaptive decoder for human interaction

Facilitated semantic alignment across systems

Abstract

One of the most significant problems which inhibits further developments in the areas of Knowledge Representation and Artificial Intelligence is a problem of semantic alignment or knowledge mapping. The progress in its solution will be greatly beneficial for further advances of information retrieval, ontology alignment, relevance calculation, text mining, natural language processing etc. In the paper the concept of multidimensional global knowledge map, elaborated through unsupervised extraction of dependencies from large documents corpus, is proposed. In addition, the problem of direct Human - Knowledge Representation System interface is addressed and a concept of adaptive decoder proposed for the purpose of interaction with previously described unified mapping model. In combination these two approaches are suggested as basis for a development of a new generation of knowledge representation systems.