Bio

Georgi Simeonov is pursuing a PhD degree in computer science. He graduated with bachelor’s and master’s degrees in informatics from Sofia University, Bulgaria, in the Faculty of Mathematics and Informatics. He is an alumnus of the Electrical Engineering Technological School under the auspices of the Technical University of Sofia.

He has a wide range of interests in research and science. His research interests include programming languages, parallel and distributed computing, cloud computing, extraction and aggregation of information, discrete mathematics, and physics.

Project: Mathematical Formulas Extraction and Search

Information and scientific resources are often disorganized, with a lack of structure or without complete metadata. These problems are worsened by the fact that mathematical notations, formulas, diagrams, and images are often almost invisible to search. The amount of data in all areas of science is so large that accessing data or knowledge without a search is unthinkable. The project is about extracting formulas from publications and preprocessing them in order to get a structured dataset. The search provided allows the user to search for math expressions, look at the articles they appear in, and possibly get definitions for the symbols involved in the expressions.

Part of a list with extracted formulas and expressions from 1,597 publications in the field of physics.

Search is possible within different forms of representation for a given example formula:

TeX Format:

k=\frac{1}{\sqrt{1-\frac{v^2}{c^2}}}

Mathematica InputForm:

Inactive[Set][k, 1/Sqrt[1 - v^2/c^2]]

Mathematica FullForm:

Inactive[Set][k,Power[Plus[1,Times[-1,Power[c,-2],Power[v,2]]],Rational[-1,2]]]

Mathematica TreeForm: