First Experiments with Neural Translation of Informal to Formal Mathematics

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.

[1]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[2]  Josef Urban,et al.  MPTP 0.2: Design, Implementation, and Initial Experiments , 2006, Journal of Automated Reasoning.

[3]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[4]  Graham Neubig,et al.  Neural Machine Translation and Sequence-to-sequence Models: A Tutorial , 2017, ArXiv.

[5]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[6]  Adam Naumowicz,et al.  Mizar: State-of-the-art and Beyond , 2015, CICM.

[7]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[8]  Grzegorz Bancerek.  Automatic translation in Formalized Mathematics , 2006 .

[9]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[10]  Cezary Kaliszyk,et al.  Developing Corpus-Based Translation Methods between Informal and Formal Mathematics: Project Description , 2014, CICM.

[11]  Cezary Kaliszyk,et al.  Learning to Parse on Aligned Corpora (Rough Diamond) , 2015, ITP.

[12]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[13]  Cezary Kaliszyk,et al.  Automating Formalization by Statistical and Semantic Parsing of Mathematics , 2017, ITP.

[14]  Cezary Kaliszyk,et al.  Hammering towards QED , 2016, J. Formaliz. Reason..

[15]  T. Hales.  Dense Sphere Packings: A Blueprint for Formal Proofs , 2012 .

[16]  Josef Urban,et al.  Theorem Proving in Large Formal Mathematics as an Emerging AI Field , 2013, Automated Reasoning and Mathematics.

[17]  David Silver,et al.  Move Evaluation in Go Using Deep Convolutional Neural Networks , 2014, ICLR.

[18]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[19]  Tobias Nipkow,et al.  A FORMAL PROOF OF THE KEPLER CONJECTURE , 2015, Forum of Mathematics, Pi.