@inproceedings{xu-etal-2024-cleaner, title = "Cleaner Pretraining Corpus Curation with Neural Web Scraping", author = "Xu, Zhipeng and Liu, Zhenghao and Yan, Yukun and Liu, Zhiyuan and Yu, Ge and Xiong, Chenyan", editor = "Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek", booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.acl-short.72/", doi = "10.18653/v1/2024.acl-short.72", pages = "802--812" }