# Distilling Wikipedia mathematical knowledge into neural network models

arXiv: https://arxiv.org/abs/2104.05930 · HTML: https://mlsanity.com/paper/2104.05930/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 11 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 4 of 4)

- [AI Feynman: a Physics-Inspired Method for Symbolic Regression](https://mlsanity.com/paper/1905.11481/) (2019)
- [Analysing Mathematical Reasoning Abilities of Neural Models](https://mlsanity.com/paper/1904.01557/) (2019)
- [Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients](https://mlsanity.com/paper/1912.04871/) (2019)
- [Deep Learning for Symbolic Mathematics](https://mlsanity.com/paper/1912.01412/) (2019)

## Built on by (most cited first, 6 of 6)

- [Generative Discovery of Partial Differential Equations by Learning from Math Handbooks](https://mlsanity.com/paper/2505.05869/) (2025)
- [CoNSoLe: Convex Neural Symbolic Learning](https://mlsanity.com/paper/2206.00257/) (2022)
- [Incorporating domain knowledge into neural-guided search](https://mlsanity.com/paper/2107.09182/) (2021)
- [A Triumvirate of AI Driven Theoretical Discovery](https://mlsanity.com/paper/2405.19973/) (2024)
- [Deep Symbolic Optimization: Reinforcement Learning for Symbolic Mathematics](https://mlsanity.com/paper/2505.10762/) (2025)
- [Generalizing the SINDy approach with nested neural networks](https://mlsanity.com/paper/2404.15742/) (2024)

## Abstract (arXiv)

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 textitmathematical textitlanguage textitmodel 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.