English

Distilling Wikipedia mathematical knowledge into neural network models

Machine Learning 2022-07-06 v1 Artificial Intelligence

Abstract

Machine learning applications to symbolic mathematics are becoming increasingly popular, yet there lacks a centralized source of real-world symbolic expressions to be used as training data. In contrast, the field of natural language processing leverages resources like Wikipedia that provide enormous amounts of real-world textual data. Adopting the philosophy of "mathematics as language," we bridge this gap by introducing a pipeline for distilling mathematical expressions embedded in Wikipedia into symbolic encodings to be used in downstream machine learning tasks. We demonstrate that a mathematical\textit{mathematical} language\textit{language} model\textit{model} trained on this "corpus" of expressions can be used as a prior to improve the performance of neural-guided search for the task of symbolic regression.

Keywords

Cite

@article{arxiv.2104.05930,
  title  = {Distilling Wikipedia mathematical knowledge into neural network models},
  author = {Joanne T. Kim and Mikel Landajuela and Brenden K. Petersen},
  journal= {arXiv preprint arXiv:2104.05930},
  year   = {2022}
}

Comments

6 pages, 4 figures

R2 v1 2026-06-24T01:06:24.963Z