Latexify Math: Mathematical Formula Markup Revision to Assist Collaborative Editing in Math Q&A Sites

TL;DR

This paper introduces MathLatexEdit, a deep learning tool designed to assist in editing mathematical formulas on math Q&A sites by translating original posts into improved versions, reducing manual effort and errors.

Contribution

The paper presents a novel deep learning approach with encoder-decoder models for LaTeX formula editing, trained on large-scale post pairs and screenshot data, to aid collaborative math content editing.

Findings

High accuracy in LaTeX formula editing tasks

Effective in real-world post revisions

Reduces manual editing time and errors

Abstract

Collaborative editing questions and answers plays an important role in quality control of Mathematics Stack Exchange which is a math Q&A Site. Our study of post edits in Mathematics Stack Exchange shows that there is a large number of math-related edits about latexifying formulas, revising LaTeX and converting the blurred math formula screenshots to LaTeX sequence. Despite its importance, manually editing one math-related post especially those with complex mathematical formulas is time-consuming and error-prone even for experienced users. To assist post owners and editors to do this editing, we have developed an edit-assistance tool, MathLatexEdit for formula latexification, LaTeX revision and screenshot transcription. We formulate this formula editing task as a translation problem, in which an original post is translated to a revised post. MathLatexEdit implements a deep learning based approach including two encoder-decoder models for textual and visual LaTeX edit recommendation with math-specific inference. The two models are trained on large-scale historical original-edited post pairs and synthesized screenshot-formula pairs. Our evaluation of MathLatexEdit not only demonstrates the accuracy of our model, but also the usefulness of MathLatexEdit in editing real-world posts which are accepted in Mathematics Stack Exchange.