Conference Papers Year : 2025

TheoremView: A Framework for Extracting Theorem-Like Environments from Raw PDFs

Abstract

This paper presents TheoremView, a novel framework for extracting proofs and theorems from raw PDF scientific papers without requiring LaTeX source files. Our approach combines three modalities (font, text, and vision) with sequential modeling to capture long-term dependencies and layout information. By eliminating OCR preprocessing, TheoremView reduces computational overhead for real-time applications while providing robust automated theorem extraction. Our framework is publicly available at https://theoremkb.org/demo, with a demonstration video at https://theoremkb.org/video.
Fichier principal
Vignette du fichier
main.pdf (1.1 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04894570 , version 1 (17-01-2025)

Licence

Identifiers

  • HAL Id : hal-04894570 , version 1

Cite

Shrey Mishra, Neil Sharma, Antoine Gauquier, Pierre Senellart. TheoremView: A Framework for Extracting Theorem-Like Environments from Raw PDFs. ECIR 2025 - European Conference on Information Retrieval, Apr 2025, Lucca, Italy. pp.6. ⟨hal-04894570⟩
0 View
0 Download

Share

More