{
 "id": "bltlab/open-ner-standardized",
 "owner": "bltlab",
 "name": "open-ner-standardized",
 "downloads": 2399,
 "likes": 2,
 "last_modified": "2025-12-19T16:47:44.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "token-classification"
 ],
 "citation": "@inproceedings{palen-michel-etal-2025-openner,\n    title = \"{O}pen{NER} 1.0: Standardized Open-Access Named Entity Recognition Datasets in 50+ Languages\",\n    author = {Palen-Michel, Chester  and\n      Pickering, Maxwell  and\n      Kruse, Maya  and\n      S{\\\"a}lev{\\\"a}, Jonne  and\n      Lignos, Constantine},\n    editor = \"Christodoulopoulos, Christos  and\n      Chakraborty, Tanmoy  and\n      Rose, Carolyn  and\n      Peng, Violet\",\n    booktitle = \"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2025\",\n    address = \"Suzhou, China\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.emnlp-main.1708/\",\n    doi = \"10.18653/v1/2025.emnlp-main.1708\",\n    pages = \"33637--33662\",\n    ISBN = \"979-8-89176-332-6\",\n    abstract = \"We present OpenNER 1.0, a standardized collection of openly-available named entity recognition (NER) datasets.OpenNER contains 36 NER corpora that span 52 languages, human-annotated in varying named entity ontologies.We correct annotation format issues, standardize the original datasets into a uniform representation with consistent entity type names across corpora, and provide the collection in a structure that enables research in multilingual and multi-ontology NER.We provide baseline results using three pretrained multilingual language models and two large language models to compare the performance of recent models and facilitate future re",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "725f738bf3a97ec102acfeec232fc5b2e54aa8ea",
 "stated_evidence": "https://huggingface.co/datasets/bltlab/open-ner-standardized/blob/725f738bf3a97ec102acfeec232fc5b2e54aa8ea/README.md",
 "file_evidence": "https://huggingface.co/datasets/bltlab/open-ner-standardized/tree/725f738bf3a97ec102acfeec232fc5b2e54aa8ea",
 "card_nc": false
}