Towards Extraction of Theorems and Proofs in Scholarly Articles - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Towards Extraction of Theorems and Proofs in Scholarly Articles

Shrey Mishra
  • Function : Author
  • PersonId : 1105903
Lucas Pluvinage
  • Function : Author
  • PersonId : 1078307

Abstract

Scholarly articles in mathematical fields often feature mathematical statements (theorems, propositions, etc.) and their proofs. In this paper, we present preliminary work for extracting such information from PDF documents, with several types of approaches: vision (using YOLO), natural language (with transformers), and styling information (with linear conditional random fields). Our main task is to identify which parts of the paper to label as theorem-like environments and proofs. We rely on a dataset collected from arXiv, with LaTeX sources of research articles used to train the models.
Fichier principal
Vignette du fichier
without_copy.pdf (1.38 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03293643 , version 1 (21-07-2021)

Identifiers

  • HAL Id : hal-03293643 , version 1

Cite

Shrey Mishra, Lucas Pluvinage, Pierre Senellart. Towards Extraction of Theorems and Proofs in Scholarly Articles. DocEng '21 - 21st ACM Symposium on Document Engineering, Aug 2021, Limerick, Ireland. ⟨hal-03293643⟩
226 View
301 Download

Share

Gmail Mastodon Facebook X LinkedIn More