Neural Machine Translation for Mathematical Formulae
This addresses the problem of precise translation for mathematical information needs, which is incremental as it applies existing methods to a new domain.
The paper tackled neural machine translation of mathematical formulae between ambiguous presentation and unambiguous content languages, achieving 95.1% and 90.7% exact match accuracy for LaTeX to Mathematica and LaTeX to semantic LaTeX tasks, respectively.
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.