@inproceedings{koto-etal-2021-indobertweet, title = "{I}ndo{BERT}weet: A Pretrained Language Model for {I}ndonesian {T}witter with Effective Domain-Specific Vocabulary Initialization", author = "Koto, Fajri and Lau, Jey Han and Baldwin, Timothy", editor = "Moens, Marie-Francine and Huang, Xuanjing and Specia, Lucia and Yih, Scott Wen-tau", booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2021", address = "Online and Punta Cana, Dominican Republic", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2021.emnlp-main.833/", doi = "10.18653/v1/2021.emnlp-main.833", pages = "10660--10668" }