{
 "id": "GEM/mlsum",
 "owner": "GEM",
 "name": "mlsum",
 "downloads": 377,
 "likes": 2,
 "last_modified": "2022-10-24T15:30:21.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "summarization"
 ],
 "citation": "@inproceedings{scialom-etal-2020-mlsum,\n    title = \"{MLSUM}: The Multilingual Summarization Corpus\",\n    author = \"Scialom, Thomas  and\n      Dray, Paul-Alexis  and\n      Lamprier, Sylvain  and\n      Piwowarski, Benjamin  and\n      Staiano, Jacopo\",\n    booktitle = \"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)\",\n    month = nov,\n    year = \"2020\",\n    address = \"Online\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2020.emnlp-main.647\",\n    doi = \"10.18653/v1/2020.emnlp-main.647\",\n    pages = \"8051--8067\",\n    abstract = \"We present MLSUM, the first large-scale MultiLingual SUMmarization dataset. Obtained from online newspapers, it contains 1.5M+ article/summary pairs in five different languages {--} namely, French, German, Spanish, Russian, Turkish. Together with English news articles from the popular CNN/Daily mail dataset, the collected data form a large scale multilingual dataset which can enable new research directions for the text summarization community. We report cross-lingual comparative analyses based on state-of-the-art systems. These highlight existing biases which motivate the use of a multi-lingual dataset.\",\n}",
 "signal": "restrictive",
 "reason": "The dataset card's licence name or licence section contains wording that suggests non-commercial, research-only or academic-only use restrictions.",
 "revision": "8a22421bf1327ac793893604a8109d65da29eabf",
 "stated_evidence": "https://huggingface.co/datasets/GEM/mlsum/blob/8a22421bf1327ac793893604a8109d65da29eabf/README.md",
 "file_evidence": "https://huggingface.co/datasets/GEM/mlsum/tree/8a22421bf1327ac793893604a8109d65da29eabf",
 "card_nc": true
}