@article{kreutzer-etal-2022-quality, title = "Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets", author = {Kreutzer, Julia and Caswell, Isaac and Wang, Lisa and Wahab, Ahsan and van Esch, Daan and Ulzii-Orshikh, Nasanbayar and Tapo, Allahsera and Subramani, Nishant and Sokolov, Artem and Sikasote, Claytone and Setyawan, Monang and Sarin, Supheakmungkol and Samb, Sokhar and Sagot, Beno{\^i}t and Rivera, Clara and Rios, Annette and Papadimitriou, Isabel and Osei, Salomey and Suarez, Pedro Ortiz and Orife, Iroro and Ogueji, Kelechi and Rubungo, Andre Niyongabo and Nguyen, Toan Q. and M{\"u}ller, Mathias and M{\"u}ller, Andr{\'e} and Muhammad, Shamsuddeen Hassan and Muhammad, Nanda and Mnyakeni, Ayanda and Mirzakhalov, Jamshidbek and Matangira, Tapiwanashe and Leong, Colin and Lawson, Nze and Kudugunta, Sneha and Jernite, Yacine and Jenny, Mathias and Firat, Orhan and Dossou, Bonaventure F. P. and Dlamini, Sakhile and de Silva, Nisansa and {\c{C}}abuk Ball{\i}, Sakine and Biderman, Stella and Battisti, Alessia and Baruwa, Ahmed and Bapna, Ankur and Baljekar, Pallavi and Azime, Israel Abebe and Awokoya, Ayodele and Ataman, Duygu and Ahia, Orevaoghene and Ahia, Oghenefego and Agrawal, Sweta and Adeyemi, Mofetoluwa}, editor = "Roark, Brian and Nenkova, Ani", journal = "Transactions of the Association for Computational Linguistics", volume = "10", year = "2022", address = "Cambridge, MA", publisher = "MIT Press", url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2022.tacl-1.4/", doi = "10.1162/tacl_a_00447", pages = "50--72" }