{
 "id": "mteb/norquad_retrieval",
 "owner": "mteb",
 "name": "norquad_retrieval",
 "downloads": 498,
 "likes": 1,
 "last_modified": "2025-05-04T16:10:52.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "@inproceedings{ivanova-etal-2023-norquad,\n  abstract = {In this paper we present NorQuAD: the first Norwegian question answering dataset for machine reading comprehension. The dataset consists of 4,752 manually created question-answer pairs. We here detail the data collection procedure and present statistics of the dataset. We also benchmark several multilingual and Norwegian monolingual language models on the dataset and compare them against human performance. The dataset will be made freely available.},\n  address = {T{\\'o}rshavn, Faroe Islands},\n  author = {Ivanova, Sardana  and\nAndreassen, Fredrik  and\nJentoft, Matias  and\nWold, Sondre  and\n{\\O}vrelid, Lilja},\n  booktitle = {Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)},\n  editor = {Alum{\\\"a}e, Tanel  and\nFishel, Mark},\n  month = may,\n  pages = {159--168},\n  publisher = {University of Tartu Library},\n  title = {{N}or{Q}u{AD}: {N}orwegian Question Answering Dataset},\n  url = {https://aclanthology.org/2023.nodalida-1.17},\n  year = {2023},\n}\n\n\n@article{enevoldsen2025mmtebmassivemultilingualtext,\n  title={MMTEB: Massive Multilingual Text Embedding Benchmark},\n  author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonath",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "c5f017bb142e2f9f87f834ebc27388cd9edfcbcd",
 "stated_evidence": "https://huggingface.co/datasets/mteb/norquad_retrieval/blob/c5f017bb142e2f9f87f834ebc27388cd9edfcbcd/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/norquad_retrieval/tree/c5f017bb142e2f9f87f834ebc27388cd9edfcbcd",
 "card_nc": false
}