mlsanityData to 7 Oct 2026

Neural Machine Translation for Mathematical Formulae

arXiv 2305.16433 ↗First posted 25 May 2023cs.CL cs.SC stat.APcited by 7

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of neural machine translation of mathematical formulae between ambiguous presentation languages and unambiguous content languages. Compared to neural machine translation on natural language, mathematical formulae have a much smaller vocabulary and much longer sequences of symbols, while their translation requires extreme precision to satisfy mathematical information needs. In this work, we perform the tasks of translating from LaTeX to Mathematica as well as from LaTeX to semantic LaTeX. While recurrent, recursive, and transformer networks struggle with preserving all contained information, we find that convolutional sequence-to-sequence networks achieve 95.1% and 90.7% exact matches, respectively.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 22 of its 40 references that are in the map. First posted on arXiv 25 May 2023.

Builds on

22 of 40 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  4. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  5. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  6. 2016Language Modeling with Gated Convolutional Networkscited by 688
  7. 2017Convolutional Sequence to Sequence Learningcited by 550
  8. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  9. 2019Deep Learning for Symbolic Mathematicscited by 266
  10. 2019Pay Less Attention with Lightweight and Dynamic Convolutionscited by 211
  11. 2018Scaling Neural Machine Translationcited by 204
  12. 2016Image-to-Markup Generation with Coarse-to-Fine Attentioncited by 79
10 more
  1. 2018Learning Longer-term Dependencies in RNNs with Auxiliary Lossescited by 58
  2. 2018First Experiments with Neural Translation of Informal to Formal Mathematicscited by 52
  3. 2016A Fast Unified Model for Parsing and Sentence Understandingcited by 34
  4. 2021Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problemscited by 30
  5. 2018Multilingual Neural Machine Translation with Task-Specific Attentioncited by 26
  6. 2018Improving the Representation and Conversion of Mathematical Formulae by Considering their Textual Contextcited by 6
  7. 2020Discovering Mathematical Objects of Interest -- A Study of Mathematical Notationscited by 4
  8. 2019Semantic Preserving Bijective Mappings for Expressions involving Special Functions in Computer Algebra Systems and Document Preparation Systemscited by 2
  9. 2015Growing the Digital Repository of Mathematical Formulae with Generic LaTeX Sourcescited by 1
  10. 2021Semantic Preserving Bijective Mappings of Mathematical Formulae between Document Preparation Systems and Computer Algebra Systemscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 4; 2026: 1.

7 papers.

  1. 2025Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitionscited by 20
  2. 2023Multi-Operational Mathematical Derivations in Latent Spacecited by 6
  3. 2025MASA: LLM-Driven Multi-Agent Systems for Autoformalizationcited by 6
  4. 2025Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMscited by 2
  5. 2025MAMUT: A Novel Framework for Modifying Mathematical Formulas for the Generation of Specialized Datasets for Language Model Trainingcited by 1
  6. 2023English to Arabic machine translation of mathematical documentscited by 0
  7. 2026MioFFAn: an Annotation Software for Formula Formalization with LLM Automation Capabilitiescited by 0