# Mathematical Language Processing Project

arXiv: https://arxiv.org/abs/1407.0167 · HTML: https://mlsanity.com/paper/1407.0167/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2014.

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

- [BERT is not The Count: Learning to Match Mathematical Statements with Proofs](https://mlsanity.com/paper/2302.09350/) (2023)
- [A Survey in Mathematical Language Processing](https://mlsanity.com/paper/2205.15231/) (2022)
- [Learning to Match Mathematical Statements with Proofs](https://mlsanity.com/paper/2102.02110/) (2021)
- [Data Augmentation Method Utilizing Template Sentences for Variable Definition Extraction](https://mlsanity.com/paper/2405.14962/) (2024)
- [E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions](https://mlsanity.com/paper/2501.14951/) (2025)
- [What Makes a Good Dataset for Symbol Description Reading?](https://mlsanity.com/paper/2304.08352/) (2023)

## Abstract (arXiv)

In natural language, words and phrases themselves imply the semantics. In contrast, the meaning of identifiers in mathematical formulae is undefined. Thus scientists must study the context to decode the meaning. The Mathematical Language Processing (MLP) project aims to support that process. In this paper, we compare two approaches to discover identifier-definition tuples. At first we use a simple pattern matching approach. Second, we present the MLP approach that uses part-of-speech tag based distances as well as sentence positions to calculate identifier-definition probabilities. The evaluation of our prototypical system, applied on the Wikipedia text corpus, shows that our approach augments the user experience substantially. While hovering the identifiers in the formula, tool-tips with the most probable definitions occur. Tests with random samples show that the displayed definitions provide a good match with the actual meaning of the identifiers.