Neural Machine Translation for Mathematical Formulae

Felix Petersen, Moritz Schubotz, Andre Greiner-Petter, Bela Gipp


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.
Anthology ID:
2023.acl-long.645
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11534–11550
Language:
URL:
https://aclanthology.org/2023.acl-long.645
DOI:
10.18653/v1/2023.acl-long.645
Bibkey:
Cite (ACL):
Felix Petersen, Moritz Schubotz, Andre Greiner-Petter, and Bela Gipp. 2023. Neural Machine Translation for Mathematical Formulae. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11534–11550, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Neural Machine Translation for Mathematical Formulae (Petersen et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.acl-long.645.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2023.acl-long.645.mp4