{
 "id": "bltlab/lr-sum",
 "owner": "bltlab",
 "name": "lr-sum",
 "downloads": 700,
 "likes": 5,
 "last_modified": "2024-12-19T21:40:27.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "summarization",
  "text-generation"
 ],
 "citation": "@inproceedings{palen-michel-lignos-2023-lr,\n    title = \"{LR}-Sum: Summarization for Less-Resourced Languages\",\n    author = \"Palen-Michel, Chester  and\n      Lignos, Constantine\",\n    editor = \"Rogers, Anna  and\n      Boyd-Graber, Jordan  and\n      Okazaki, Naoaki\",\n    booktitle = \"Findings of the Association for Computational Linguistics: ACL 2023\",\n    month = jul,\n    year = \"2023\",\n    address = \"Toronto, Canada\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.findings-acl.427\",\n    doi = \"10.18653/v1/2023.findings-acl.427\",\n    pages = \"6829--6844\",\n    abstract = \"We introduce LR-Sum, a new permissively-licensed dataset created with the goal of enabling further research in automatic summarization for less-resourced languages.LR-Sum contains human-written summaries for 40 languages, many of which are less-resourced. We describe our process for extracting and filtering the dataset from the Multilingual Open Text corpus (Palen-Michel et al., 2022).The source data is public domain newswire collected from from Voice of America websites, and LR-Sum is released under a Creative Commons license (CC BY 4.0), making it one of the most openly-licensed multilingual summarization datasets. We describe abstractive and extractive summarization experiments to establish baselines and discuss the limitations of this dataset.\",\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "deb2e73ce53e42ceda31297a991afa138ee665a8",
 "stated_evidence": "https://huggingface.co/datasets/bltlab/lr-sum/blob/deb2e73ce53e42ceda31297a991afa138ee665a8/README.md",
 "file_evidence": "https://huggingface.co/datasets/bltlab/lr-sum/tree/deb2e73ce53e42ceda31297a991afa138ee665a8",
 "card_nc": false
}