@inproceedings{hoy-etal-2025-latexmt,
title = "{L}a{T}e{XMT}: Machine Translation for {L}a{T}e{X} Documents",
author = "Hoy, Calvin and
Frontull, Samuel and
Moser, Georg",
editor = {Habernal, Ivan and
Schulam, Peter and
Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-demos.56/",
pages = "739--748",
ISBN = "979-8-89176-334-0",
abstract = "While machine translation has taken great strides in recent years, thanks in large part to transformer language models, machine translation tools are designed primarily for plain text, and thus not equipped to deal with complex markup documents. Not even Large Language Models can reliably handle LaTeX source files, as non-standard structures are not captured by any available training data. Previous attempts to create translation engines for LaTeX either work on compiled documents, rely on document pre-processors which may lose critical semantic elements, or cannot distinguish between text and non-text content. In this paper we present LaTeXMT, a software solution for structure-preserving, source-to-source translation of LaTeX documents. All of the source code to LaTeXMT is provided under the LGPL-3.0 open-source licence and a web version is publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoy-etal-2025-latexmt">
<titleInfo>
<title>LaTeXMT: Machine Translation for LaTeX Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Calvin</namePart>
<namePart type="family">Hoy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Frontull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Moser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Habernal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Schulam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-334-0</identifier>
</relatedItem>
<abstract>While machine translation has taken great strides in recent years, thanks in large part to transformer language models, machine translation tools are designed primarily for plain text, and thus not equipped to deal with complex markup documents. Not even Large Language Models can reliably handle LaTeX source files, as non-standard structures are not captured by any available training data. Previous attempts to create translation engines for LaTeX either work on compiled documents, rely on document pre-processors which may lose critical semantic elements, or cannot distinguish between text and non-text content. In this paper we present LaTeXMT, a software solution for structure-preserving, source-to-source translation of LaTeX documents. All of the source code to LaTeXMT is provided under the LGPL-3.0 open-source licence and a web version is publicly available.</abstract>
<identifier type="citekey">hoy-etal-2025-latexmt</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-demos.56/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>739</start>
<end>748</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LaTeXMT: Machine Translation for LaTeX Documents
%A Hoy, Calvin
%A Frontull, Samuel
%A Moser, Georg
%Y Habernal, Ivan
%Y Schulam, Peter
%Y Tiedemann, Jörg
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-334-0
%F hoy-etal-2025-latexmt
%X While machine translation has taken great strides in recent years, thanks in large part to transformer language models, machine translation tools are designed primarily for plain text, and thus not equipped to deal with complex markup documents. Not even Large Language Models can reliably handle LaTeX source files, as non-standard structures are not captured by any available training data. Previous attempts to create translation engines for LaTeX either work on compiled documents, rely on document pre-processors which may lose critical semantic elements, or cannot distinguish between text and non-text content. In this paper we present LaTeXMT, a software solution for structure-preserving, source-to-source translation of LaTeX documents. All of the source code to LaTeXMT is provided under the LGPL-3.0 open-source licence and a web version is publicly available.
%U https://aclanthology.org/2025.emnlp-demos.56/
%P 739-748
Markdown (Informal)
[LaTeXMT: Machine Translation for LaTeX Documents](https://aclanthology.org/2025.emnlp-demos.56/) (Hoy et al., EMNLP 2025)
ACL
- Calvin Hoy, Samuel Frontull, and Georg Moser. 2025. LaTeXMT: Machine Translation for LaTeX Documents. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 739–748, Suzhou, China. Association for Computational Linguistics.