@article{glotccanopenbroadcoveragecommoncrawl, title = {GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages}, author = {Amir Hossein Kargaran and François Yvon and Hinrich Schütze}, year = {2024}, eprint = {2410.23825}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.23825v1}, }