Moritz Schubotz
2023
Neural Machine Translation for Mathematical Formulae
Felix Petersen

Moritz Schubotz

Andre GreinerPetter

Bela Gipp
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
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 sequencetosequence networks achieve 95.1% and 90.7% exact matches, respectively.
2022
Proceedings of the 1st Workshop on Mathematical Natural Language Processing (MathNLP)
Deborah Ferreira

Marco Valentino

Andre Freitas

Sean Welleck

Moritz Schubotz
Proceedings of the 1st Workshop on Mathematical Natural Language Processing (MathNLP)
Search
Coauthors
 Felix Petersen 1
 André GreinerPetter 1
 Bela Gipp 1
 Deborah Ferreira 1
 Marco Valentino 1
 show all...