First Experiments with Neural Translation of Informal to Formal Mathematics

Qingxiang Wang, Cezary Kaliszyk, Josef Urban

11th International Conference on Intelligent Computer Mathematics, LNCS 11006, pp. 255 – 270, 2018.


We report on our experiments to train deep neural networks that automatically translate informalized LaTeX-written Mizar texts into the formal Mizar language. To the best of our knowledge, this is the first time when neural networks have been adopted in the formalization of mathematics. Using Luong et al.’s neural machine translation model (NMT), we tested our aligned informal-formal corpora against various hyperparameters and evaluated their results. Our experiments show that our best performing model configurations are able to generate correct Mizar statements on 65.73% of the inference data, with the union of all models covering 79.17%. These results indicate that formalization through artificial neural network is a promising approach for automated formalization of mathematics. We present several case studies to illustrate our results.


  PDF |    doi:10.1007/978-3-319-96812-4_22  |  ©  Springer International Publishing AG, part of Springer Nature 2018


author = {Qingxiang Wang and
Cezary Kaliszyk and
Josef Urban},
title = {First Experiments with Neural Translation of Informal to Formal Mathematics},
booktitle = {11th International Conference on Intelligent Computer Mathematics (CICM 2018)},
pages = {255--270},
year = {2018},
url = {\_22},
doi = {10.1007/978-3-319-96812-4\_22},
editor = {Florian Rabe and
William M. Farmer and
Grant O. Passmore and
Abdou Youssef},
series = {LNCS},
volume = {11006},
publisher = {Springer},
Nach oben scrollen