@inproceedings{lucy-etal-2024-aboutme, title = "{A}bout{M}e: Using Self-Descriptions in Webpages to Document the Effects of {E}nglish Pretraining Data Filters", author = "Lucy, Li and Gururangan, Suchin and Soldaini, Luca and Strubell, Emma and Bamman, David and Klein, Lauren and Dodge, Jesse", editor = "Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek", booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.acl-long.400/", doi = "10.18653/v1/2024.acl-long.400", pages = "7393--7420" }