Mathematical Reasoning via Self-supervised Skip-tree Training [article]

Markus N. Rabe and Dennis Lee and Kshitij Bansal and Christian Szegedy
2020 arXiv   pre-print
We examine whether self-supervised language modeling applied to mathematical formulas enables logical reasoning. We suggest several logical reasoning tasks that can be used to evaluate language models trained on formal mathematical statements, such as type inference, suggesting missing assumptions and completing equalities. To train language models for formal mathematics, we propose a novel skip-tree task. We find that models trained on the skip-tree task show surprisingly strong mathematical
more » ... asoning abilities, and outperform models trained on standard skip-sequence tasks. We also analyze the models' ability to formulate new conjectures by measuring how often the predictions are provable and useful in other proofs.
arXiv:2006.04757v3 fatcat:yrmqpmijjzh6rcnkm3b77k3mwy