@inproceedings{lin-etal-2024-fineweb, title = "{F}ine{W}eb-zhtw: Scalable Curation of Traditional {C}hinese Text Data from the Web", author = "Lin, Cheng-Wen and Hsieh, Wan-Hsuan and Guan, Kai-Xin and Hsu, Chan-Jan and Kuo, Chia-Chen and Lai, Chuan-Lin and Chung, Chung-Wei and Wang, Ming-Jen and Shiu, Da-Shan", editor = "Tseng, Shu-Chuan and Tsao, Yu and Huang, Hen-Hsen and Fan, Yao-Chung and Chang, Chia-Hui", booktitle = "Proceedings of the 36th Conference on Computational Linguistics and Speech Processing (ROCLING 2024)", month = nov, year = "2024", address = "Taipei City, Taiwan", publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)", url = "https://aclanthology.org/2024.rocling-1.16/", pages = "129--136" }