{
 "id": "NbAiLab/norwegian_parliament",
 "owner": "NbAiLab",
 "name": "norwegian_parliament",
 "downloads": 411,
 "likes": 6,
 "last_modified": "2024-04-16T08:15:10.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{kummervold-etal-2021-operationalizing,\ntitle = {Operationalizing a National Digital Library: The Case for a {N}orwegian Transformer Model},\nauthor = {Kummervold, Per E  and\nDe la Rosa, Javier  and\nWetjen, Freddy  and\nBrygfjeld, Svein Arne\",\nbooktitle = {Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)},\nyear = \"2021\",\naddress = \"Reykjavik, Iceland (Online)\",\npublisher = {Link{\"o}ping University Electronic Press, Sweden},\nurl = \"https://aclanthology.org/2021.nodalida-main.3\",\npages = \"20--29\",\nabstract = \"In this work, we show the process of building a large-scale training set from digital and digitized collections at a national library.\nThe resulting Bidirectional Encoder Representations from Transformers (BERT)-based language model for Norwegian outperforms multilingual BERT (mBERT) models\nin several token and sequence classification tasks for both Norwegian Bokm{aa}l and Norwegian Nynorsk. Our model also improves the mBERT performance for other\nlanguages present in the corpus such as English, Swedish, and Danish. For languages not included in the corpus, the weights degrade moderately while keeping strong multilingual properties. Therefore,\nwe show that building high-quality models within a memory institution using somewhat noisy optical character recognition (OCR) content is feasible, and we hope to pave the way for other memory institutions to follow.\",\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "dbb886251767e29bec7b2a2686b6d0787ebdd3aa",
 "stated_evidence": "https://huggingface.co/datasets/NbAiLab/norwegian_parliament/blob/dbb886251767e29bec7b2a2686b6d0787ebdd3aa/README.md",
 "file_evidence": "https://huggingface.co/datasets/NbAiLab/norwegian_parliament/tree/dbb886251767e29bec7b2a2686b6d0787ebdd3aa",
 "card_nc": false
}