@inproceedings{de-gibert-etal-2024-new, title = "A New Massive Multilingual Dataset for High-Performance Language Technologies", author = {de Gibert, Ona and Nail, Graeme and Arefyev, Nikolay and Ba{\~n}{\'o}n, Marta and van der Linde, Jelmer and Ji, Shaoxiong and Zaragoza-Bernabeu, Jaume and Aulamo, Mikko and Ram{\'i}rez-S{\'a}nchez, Gema and Kutuzov, Andrey and Pyysalo, Sampo and Oepen, Stephan and Tiedemann, J{\"o}rg}, editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://preview.aclanthology.org/fix-sig-urls/2024.lrec-main.100/", pages = "1116--1128" }