{
 "id": "Babelscape/multinerd",
 "owner": "Babelscape",
 "name": "multinerd",
 "downloads": 2295,
 "likes": 27,
 "last_modified": "2023-04-20T12:43:31.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "token-classification"
 ],
 "citation": "@inproceedings{tedeschi-navigli-2022-multinerd,\n    title = \"{M}ulti{NERD}: A Multilingual, Multi-Genre and Fine-Grained Dataset for Named Entity Recognition (and Disambiguation)\",\n    author = \"Tedeschi, Simone  and\n      Navigli, Roberto\",\n    booktitle = \"Findings of the Association for Computational Linguistics: NAACL 2022\",\n    month = jul,\n    year = \"2022\",\n    address = \"Seattle, United States\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2022.findings-naacl.60\",\n    doi = \"10.18653/v1/2022.findings-naacl.60\",\n    pages = \"801--812\",\n    abstract = \"Named Entity Recognition (NER) is the task of identifying named entities in texts and classifying them through specific semantic categories, a process which is crucial for a wide range of NLP applications. Current datasets for NER focus mainly on coarse-grained entity types, tend to consider a single textual genre and to cover a narrow set of languages, thus limiting the general applicability of NER systems.In this work, we design a new methodology for automatically producing NER annotations, and address the aforementioned limitations by introducing a novel dataset that covers 10 languages, 15 NER categories and 2 textual genres.We also introduce a manually-annotated test set, and extensively evaluate the quality of our novel dataset on both this new test set and standard benchmarks for NER.In addition, in our dataset, we include: i) disambiguation information to enable ",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "2814b78e7af4b5a1f1886fe7ad49632de4d9dd25",
 "stated_evidence": "https://huggingface.co/datasets/Babelscape/multinerd/blob/2814b78e7af4b5a1f1886fe7ad49632de4d9dd25/README.md",
 "file_evidence": "https://huggingface.co/datasets/Babelscape/multinerd/tree/2814b78e7af4b5a1f1886fe7ad49632de4d9dd25",
 "card_nc": false
}