@misc{wenzek2019ccnet, title={CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data}, author={Guillaume Wenzek and Marie-Anne Lachaux and Alexis Conneau and Vishrav Chaudhary and Francisco Guzmán and Armand Joulin and Edouard Grave}, year={2019}, eprint={1911.00359}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/1911.00359} }