@inproceedings{liu-etal-2024-ofa, title = "{OFA}: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining", author = "Liu, Yihong and Lin, Peiqin and Wang, Mingyang and Schuetze, Hinrich", editor = "Duh, Kevin and Gomez, Helena and Bethard, Steven", booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024", month = jun, year = "2024", address = "Mexico City, Mexico", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.findings-naacl.68/", doi = "10.18653/v1/2024.findings-naacl.68", pages = "1067--1097" }