Mathematical Language Processing Project

TL;DR

The paper introduces the Mathematical Language Processing (MLP) project, which enhances understanding of mathematical identifiers by using context-aware methods to suggest definitions, improving user experience in decoding mathematical texts.

Contribution

It presents a novel approach combining POS-based distances and sentence positions for identifier-definition extraction, outperforming simple pattern matching methods.

Findings

The MLP approach significantly improves identifier-definition matching accuracy.

User experience is enhanced through effective tooltip suggestions.

Evaluation shows high relevance of suggested definitions in Wikipedia texts.

Abstract

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.