MathGloss: Building mathematical glossaries from text

TL;DR

MathGloss is an automated system that constructs a comprehensive knowledge graph of undergraduate mathematics concepts by integrating multiple online resources, facilitating personalized learning and bridging formal and informal mathematical knowledge.

Contribution

It introduces a novel approach to automatically building a mathematical knowledge graph by combining diverse online resources and NLP tools, enhancing accessibility and interoperability.

Findings

Integrated five major mathematical resources into a unified KG.

Enabled personalized learning pathways for students and mathematicians.

Facilitated communication between informal and formal mathematical systems.

Abstract

MathGloss is a project to create a knowledge graph (KG) for undergraduate mathematics from text, automatically, using modern natural language processing (NLP) tools and resources already available on the web. MathGloss is a linked database of undergraduate concepts in mathematics. So far, it combines five resources: (i) Wikidata, a collaboratively edited, multilingual knowledge graph hosted by the Wikimedia Foundation, (ii) terms covered in mathematics courses at the University of Chicago, (iii) the syllabus of the French undergraduate mathematics curriculum which includes hyperlinks to the automated theorem prover Lean 4, (iv) MuLiMa, a multilingual dictionary of mathematics curated by mathematicians, and (v) the nLab, a wiki for category theory also curated by mathematicians. MathGloss's goal is to bring together resources for learning mathematics and to allow every mathematician to tailor their learning to their own preferences. Moreover, by organizing different resources for learning undergraduate mathematics alongside those for learning formal mathematics, we hope to make it easier for mathematicians and formal tools (theorem provers, computer algebra systems, etc) experts to "understand" each other and break down some of the barriers to formal math.