English

Learning to Match Mathematical Statements with Proofs

Computation and Language 2021-02-04 v1

Abstract

We introduce a novel task consisting in assigning a proof to a given mathematical statement. The task is designed to improve the processing of research-level mathematical texts. Applying Natural Language Processing (NLP) tools to research level mathematical articles is both challenging, since it is a highly specialized domain which mixes natural language and mathematical formulae. It is also an important requirement for developing tools for mathematical information retrieval and computer-assisted theorem proving. We release a dataset for the task, consisting of over 180k statement-proof pairs extracted from mathematical research articles. We carry out preliminary experiments to assess the difficulty of the task. We first experiment with two bag-of-words baselines. We show that considering the assignment problem globally and using weighted bipartite matching algorithms helps a lot in tackling the task. Finally, we introduce a self-attention-based model that can be trained either locally or globally and outperforms baselines by a wide margin.

Keywords

Cite

@article{arxiv.2102.02110,
  title  = {Learning to Match Mathematical Statements with Proofs},
  author = {Maximin Coavoux and Shay B. Cohen},
  journal= {arXiv preprint arXiv:2102.02110},
  year   = {2021}
}
R2 v1 2026-06-23T22:48:14.536Z