@inproceedings{parmar-etal-2024-data,
    title = "Data, Data Everywhere: A Guide for Pretraining Dataset Construction",
    author = "Parmar, Jupinder  and
      Prabhumoye, Shrimai  and
      Jennings, Joseph  and
      Liu, Bo  and
      Jhunjhunwala, Aastha  and
      Wang, Zhilin  and
      Patwary, Mostofa  and
      Shoeybi, Mohammad  and
      Catanzaro, Bryan",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.596/",
    doi = "10.18653/v1/2024.emnlp-main.596",
    pages = "10671--10695"
}