@inproceedings{ogunremi-etal-2023-mini, title = "Mini But Mighty: Efficient Multilingual Pretraining with Linguistically-Informed Data Selection", author = "Ogunremi, Tolulope and Jurafsky, Dan and Manning, Christopher", editor = "Vlachos, Andreas and Augenstein, Isabelle", booktitle = "Findings of the Association for Computational Linguistics: EACL 2023", month = may, year = "2023", address = "Dubrovnik, Croatia", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2023.findings-eacl.93/", doi = "10.18653/v1/2023.findings-eacl.93", pages = "1251--1266" }