Neural Machine Translation for Mathematical Formulae

Felix Petersen, Moritz Schubotz, Andre Greiner-Petter, Bela Gipp
5/25/2023
cs.CLcs.SCstat.AP

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Prompting Neural Machine Translation with Translation Memories

80% match2023

Distinguishing Translations by Human, NMT, and ChatGPT: A Linguistic and Statistical Approach

80% match2023

Hindi to English: Transformer-Based Neural Machine Translation

80% match2023

Dual Branch Network Towards Accurate Printed Mathematical Expression Recognition

79% match2023

Neural Machine Translation with Dynamic Graph Convolutional Decoder

79% match2023

Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translation

79% match2023

Cite this paper

@article{petersen2023neural,
  title  = {Neural Machine Translation for Mathematical Formulae},
  author = {Felix Petersen and Moritz Schubotz and Andre Greiner-Petter and Bela Gipp},
  year   = {2023},
  eprint = {2305.16433},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.16433v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.16433.svg)](https://codeofpaper.com/paper/2305.16433)

Discussion