@inproceedings{guan-etal-2025-prep, title = "{P}re{P}-{OCR}: A Complete Pipeline for Document Image Restoration and Enhanced {OCR} Accuracy", author = "Guan, Shuhao and Lin, Moule and Xu, Cheng and Liu, Xinyi and Zhao, Jinman and Fan, Jiexin and Xu, Qi and Greene, Derek", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.749/", pages = "15413--15425", ISBN = "979-8-89176-251-0" }