{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","url":"https://codeofpaper.com/paper/1911.00359","arxiv_url":"https://arxiv.org/abs/1911.00359","published":"2019-11-01","code":"official","best":{"full_name":"facebookresearch/cc_net","url":"https://github.com/facebookresearch/cc_net","tier":"official","stars":1045,"license":"MIT","framework":null,"language":"Python","last_commit":"2023-04-25T08:02:37"},"most_starred_community":null,"implementations":[{"full_name":"facebookresearch/cc_net","url":"https://github.com/facebookresearch/cc_net","tier":"official","stars":1045,"license":"MIT","framework":null,"language":"Python","last_commit":"2023-04-25T08:02:37"}],"possible_matches":0}