INTELLIGENT SYSTEMS AND TECHNOLOGIES

Semantic formula search service for a collection of mathematical PDF documents

K. S. Nikolaev

National Research Centre "Kurchatov Institute", Moscow

Abstract: This paper presents a service based on Semantic Web technologies that allows searching mathematical formulas in a collection of scientific PDF documents. The search for formulas is performed by searching for the concepts included in the mathematical formula. In this regard, the search results do not depend on the author's designations of formula variables and contain all formulas that contain the concept from the search query. A distinctive feature of the service is the possibility of extending the collection of documents with scientific articles in PDF format without explicit markup of mathematical formulas. OntoMathPro, an ontology of professional mathematics covering a wide range of mathematics fields, is used as a source of concepts.

Keywords: semantic formula search, PDF documents, document processing, scientific journals, scientific libraries, ontologies, web service.

DOI: 10.14357/20718632250304

Bibliographic databases:

•