Advertisement

First Experiments with Neural Translation of Informal to Formal Mathematics

  • Qingxiang Wang
  • Cezary Kaliszyk
  • Josef Urban
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11006)

Abstract

We report on our experiments to train deep neural networks that automatically translate informalized Open image in new window -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.

References

  1. 1.
    Bancerek, G.: Automatic translation in formalized mathematics. Mech. Math. Appl. 5(2), 19–31 (2006)Google Scholar
  2. 2.
    Bancerek, G., et al.: Mizar: state-of-the-art and beyond. In: Kerber, M., Carette, J., Kaliszyk, C., Rabe, F., Sorge, V. (eds.) CICM 2015. LNCS (LNAI), vol. 9150, pp. 261–279. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-20615-8_17CrossRefGoogle Scholar
  3. 3.
    Bancerek, G., Carlson, P.: Mizar and the machine translation of mathematics documents (1994). http://www.mizar.org/project/banc_carl93.ps
  4. 4.
    Blanchette, J.C., Kaliszyk, C., Paulson, L.C., Urban, J.: Hammering towards QED. J. Formaliz. Reason. 9(1), 101–148 (2016)MathSciNetGoogle Scholar
  5. 5.
    Cho, K., van Merriënboer, B., Gülçehre, Ç., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734. Association for Computational Linguistics, October 2014Google Scholar
  6. 6.
    Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control Sig. Syst. 2(4), 303–314 (1989)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.orgzbMATHGoogle Scholar
  8. 8.
    Hales, T.: Dense Sphere Packings: A Blueprint for Formal Proofs. London Mathematical Society Lecture Note Series, vol. 400. Cambridge University Press, Cambridge (2012)CrossRefGoogle Scholar
  9. 9.
    Hales, T.C., Adams, M., Bauer, G., Dang, D.T., Harrison, J., Hoang, T.L., Kaliszyk, C., Magron, V., McLaughlin, S., Nguyen, T.T., Nguyen, T.Q., Nipkow, T., Obua, S., Pleso, J., Rute, J., Solovyev, A., Ta, A.H.T., Tran, T.N., Trieu, D.T., Urban, J., Vu, K.K., Zumkeller, R.: A formal proof of the Kepler conjecture. Forum Math. Pi 5, e2 (2017)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Netw. 4(2), 251–257 (1991)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Kaliszyk, C., Urban, J., Vyskočil, J.: Automating formalization by statistical and semantic parsing of mathematics. In: Ayala-Rincón, M., Muñoz, C.A. (eds.) ITP 2017. LNCS, vol. 10499, pp. 12–27. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66107-0_2CrossRefGoogle Scholar
  12. 12.
    Kaliszyk, C., Urban, J., Vyskočil, J.: Learning to parse on aligned corpora (rough diamond). In: Urban, C., Zhang, X. (eds.) ITP 2015. LNCS, vol. 9236, pp. 227–233. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-22102-1_15CrossRefGoogle Scholar
  13. 13.
    Kaliszyk, C., Urban, J., Vyskočil, J., Geuvers, H.: Developing corpus-based translation methods between informal and formal mathematics: project description. In: Watt, S.M., Davenport, J.H., Sexton, A.P., Sojka, P., Urban, J. (eds.) CICM 2014. LNCS (LNAI), vol. 8543, pp. 435–439. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-08434-3_34CrossRefzbMATHGoogle Scholar
  14. 14.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097–1105. Curran Associates Inc., New York (2012)Google Scholar
  15. 15.
    Luong, M., Brevdo, E., Zhao, R.: Neural machine translation (seq2seq) tutorial (2017). https://github.com/tensorflow/nmt
  16. 16.
    Maddison, C.J., Huang, A., Sutskever, I., Silver, D.: Move evaluation in Go using deep convolutional neural networks. CoRR, abs/1412.6564 (2014)Google Scholar
  17. 17.
    Neubig, G.: Neural machine translation and sequence-to-sequence models: a tutorial. CoRR, abs/1703.01619 (2017)Google Scholar
  18. 18.
    Olah, C.: Understanding LSTM networks. http://colah.github.io/posts/2015-08-Understanding-LSTMs/
  19. 19.
    Papineni, K., Roukos, S., Ward, T., Zhu, W.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–318. ACL (2002)Google Scholar
  20. 20.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, NIPS 2014, vol. 2, pp. 3104–3112. MIT Press, Cambridge (2014)Google Scholar
  21. 21.
    Trybulec, A., Rudnicki, P.: A collection of TeXed Mizar abstracts (1989). http://www.mizar.org/project/TR-89-18.pdf
  22. 22.
    Urban, J.: MPTP 0.2: design, implementation, and initial experiments. J. Autom. Reason. 37(1–2), 21–43 (2006)zbMATHGoogle Scholar
  23. 23.
    Urban, J., Vyskočil, J.: Theorem proving in large formal mathematics as an emerging AI field. In: Bonacina, M.P., Stickel, M.E. (eds.) Automated Reasoning and Mathematics: Essays in Memory of William W. McCune. LNCS (LNAI), vol. 7788, pp. 240–257. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-36675-8_13CrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.University of InnsbruckInnsbruckAustria
  2. 2.Czech Technical University in PraguePragueCzech Republic

Personalised recommendations