Saved in:
Bibliographic Details
Main Authors: Patel, Nilay, Saha, Rahul, Flanigan, Jeffrey
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.07957
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914863560785920
author Patel, Nilay
Saha, Rahul
Flanigan, Jeffrey
author_facet Patel, Nilay
Saha, Rahul
Flanigan, Jeffrey
contents Verifying mathematical proofs is difficult, but can be automated with the assistance of a computer. Autoformalization is the task of automatically translating natural language mathematics into a formal language that can be verified by a program. This is a challenging task, and especially for higher-level mathematics found in research papers. Research paper mathematics requires large amounts of background and context. In this paper, we propose an avenue towards tackling autoformalization for research-level mathematics, by breaking the task into easier and more approachable subtasks: unlinked formalization (formalization with unlinked definitions and theorems), entity linking (linking to the proper theorems and definitions), and finally adjusting types so it passes the type checker. In addition, we present arXiv2Formal, a benchmark dataset for unlinked formalization consisting of 50 theorems formalized for the Lean theorem prover sampled from papers on arXiv.org. We welcome any contributions from the community to future versions of this dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2310_07957
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A New Approach Towards Autoformalization
Patel, Nilay
Saha, Rahul
Flanigan, Jeffrey
Computation and Language
Artificial Intelligence
Verifying mathematical proofs is difficult, but can be automated with the assistance of a computer. Autoformalization is the task of automatically translating natural language mathematics into a formal language that can be verified by a program. This is a challenging task, and especially for higher-level mathematics found in research papers. Research paper mathematics requires large amounts of background and context. In this paper, we propose an avenue towards tackling autoformalization for research-level mathematics, by breaking the task into easier and more approachable subtasks: unlinked formalization (formalization with unlinked definitions and theorems), entity linking (linking to the proper theorems and definitions), and finally adjusting types so it passes the type checker. In addition, we present arXiv2Formal, a benchmark dataset for unlinked formalization consisting of 50 theorems formalized for the Lean theorem prover sampled from papers on arXiv.org. We welcome any contributions from the community to future versions of this dataset.
title A New Approach Towards Autoformalization
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2310.07957