First Experiments with Neural Translation of Informal to Formal Mathematics

@inproceedings{Wang2018FirstEW,
  title={First Experiments with Neural Translation of Informal to Formal Mathematics},
  author={Q. Wang and C. Kaliszyk and J. Urban},
  booktitle={CICM},
  year={2018}
}
  • Q. Wang, C. Kaliszyk, J. Urban
  • Published in CICM 2018
  • Computer Science
  • 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… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Guiding Theorem Proving by Recurrent Neural Networks
    4
    Can Neural Networks Learn Symbolic Rewriting?
    4
    Guiding Inferences in Connection Tableau by Recurrent Neural Networks.
    Stateful Premise Selection by Recurrent Neural Networks
    2
    A Survey of Languages for Formalizing Mathematics

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES
    Automating Formalization by Statistical and Semantic Parsing of Mathematics
    13
    Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
    86
    Sequence to Sequence Learning with Neural Networks
    10133
    Hammering towards QED
    96
    Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
    9045
    Learning to Parse on Aligned Corpora (Rough Diamond)
    16
    Bleu: a Method for Automatic Evaluation of Machine Translation
    11682
    Theorem Proving in Large Formal Mathematics as an Emerging AI Field
    23
    Automatic translation in Formalized Mathematics
    11