{
 "id": "GroNLP/squad-nl-v1.1",
 "owner": "GroNLP",
 "name": "squad-nl-v1.1",
 "downloads": 24,
 "likes": 0,
 "last_modified": "2024-12-20T12:10:08.000Z",
 "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": [
  "question-answering"
 ],
 "citation": "@inproceedings{de-vries-etal-2023-dumb,\n    title = \"{DUMB}: A Benchmark for Smart Evaluation of {D}utch Models\",\n    author = \"de Vries, Wietse  and\n      Wieling, Martijn  and\n      Nissim, Malvina\",\n    editor = \"Bouamor, Houda  and\n      Pino, Juan  and\n      Bali, Kalika\",\n    booktitle = \"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing\",\n    month = dec,\n    year = \"2023\",\n    address = \"Singapore\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.emnlp-main.447\",\n    doi = \"10.18653/v1/2023.emnlp-main.447\",\n    pages = \"7221--7241\",\n    abstract = \"We introduce the Dutch Model Benchmark: DUMB. The benchmark includes a diverse set of datasets for low-, medium- and high-resource tasks. The total set of nine tasks includes four tasks that were previously not available in Dutch. Instead of relying on a mean score across tasks, we propose Relative Error Reduction (RER), which compares the DUMB performance of language models to a strong baseline which can be referred to in the future even when assessing different sets of language models. Through a comparison of 14 pre-trained language models (mono- and multi-lingual, of varying sizes), we assess the internal consistency of the benchmark tasks, as well as the factors that likely enable high performance. Our results indicate that current Dutch monolingual models under-perform and suggest training larger Dutch models with other architect",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "7e1167c6ba074b3aedcd11061b0a921d5383106d",
 "stated_evidence": "https://huggingface.co/datasets/GroNLP/squad-nl-v1.1/blob/7e1167c6ba074b3aedcd11061b0a921d5383106d/README.md",
 "file_evidence": "https://huggingface.co/datasets/GroNLP/squad-nl-v1.1/tree/7e1167c6ba074b3aedcd11061b0a921d5383106d",
 "card_nc": false
}