# Preliminary Exploration of Formula Embedding for Mathematical Information Retrieval: can mathematical formulae be embedded like a natural language?

arXiv: https://arxiv.org/abs/1707.05154 · HTML: https://mlsanity.com/paper/1707.05154/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2017.

## Built on by (most cited first, 3 of 3)

- [Semantic Representations of Mathematical Expressions in a Continuous Vector Space](https://mlsanity.com/paper/2211.08142/) (2022)
- [E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions](https://mlsanity.com/paper/2501.14951/) (2025)
- [Syntax Meets Semantics: Understanding Scientific Formulae](https://mlsanity.com/paper/2608.02457/) (2026)

## Abstract (arXiv)

While neural network approaches are achieving breakthrough performance in the natural language related fields, there have been few similar attempts at mathematical language related tasks. In this study, we explore the potential of applying neural representation techniques to Mathematical Information Retrieval (MIR) tasks. In more detail, we first briefly analyze the characteristic differences between natural language and mathematical language. Then we design a "symbol2vec" method to learn the vector representations of formula symbols (numbers, variables, operators, functions, etc.) Finally, we propose a "formula2vec" based MIR approach and evaluate its performance. Preliminary experiment results show that there is a promising potential for applying formula embedding models to mathematical language representation and MIR tasks.