Machine Translation of Mathematical Text

TL;DR

The paper presents the PolyMath Translator, a system that translates LaTeX documents with mathematical content from English to French, achieving high accuracy and producing ready-to-compile LaTeX PDFs, combining Transformer models and Google Translate as backup.

Contribution

It introduces a novel translation system for mathematical LaTeX documents that integrates Transformer models with Google Translate for improved accuracy and reliability.

Findings

Achieved a BLEU score of 53.5 on test corpus.

Uses both Transformer model and Google Translate with 26% fallback rate.

Produces LaTeX documents that compile to PDF without editing.

Abstract

We have implemented a machine translation system, the PolyMath Translator, for LaTeX documents containing mathematical text. The current implementation translates English LaTeX to French LaTeX, attaining a BLEU score of 53.5 on a held-out test corpus of mathematical sentences. It produces LaTeX documents that can be compiled to PDF without further editing. The system first converts the body of an input LaTeX document into English sentences containing math tokens, using the pandoc universal document converter to parse LaTeX input. We have trained a Transformer-based translator model, using OpenNMT, on a combined corpus containing a small proportion of domain-specific sentences. Our full system uses both this Transformer model and Google Translate, the latter being used as a backup to better handle linguistic features that do not appear in our training dataset. If the Transformer model does not have confidence in its translation, as determined by a high perplexity score, then we use Google Translate with a custom glossary. This backup was used 26% of the time on our test corpus of mathematical sentences. The PolyMath Translator is available as a web service at www.polymathtrans.ai.