@inproceedings{gururangan-etal-2022-whose, title = "Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection", author = "Gururangan, Suchin and Card, Dallas and Dreier, Sarah and Gade, Emily and Wang, Leroy and Wang, Zeyu and Zettlemoyer, Luke and Smith, Noah A.", editor = "Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue", booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing", month = dec, year = "2022", address = "Abu Dhabi, United Arab Emirates", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2022.emnlp-main.165/", doi = "10.18653/v1/2022.emnlp-main.165", pages = "2562--2580" }