@inproceedings{documentingtheenglishcolossalclean,
  title = {Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus},
  author = {Jesse Dodge and Maarten Sap and Ana Marasović and William Agnew and Gabriel Ilharco and Dirk Groeneveld and Margaret Mitchell and Matt Gardner},
  year = {2021},
  booktitle = {EMNLP 2021 11},
  eprint = {2104.08758},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2104.08758v2},
}