{
 "id": "taln-ls2n/Adminset",
 "owner": "taln-ls2n",
 "name": "Adminset",
 "downloads": 304,
 "likes": 1,
 "last_modified": "2025-02-06T09:41:25.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{sebbag-etal-2025-adminset,\n    title = \"{A}dmin{S}et and {A}dmin{BERT}: a Dataset and a Pre-trained Language Model to Explore the Unstructured Maze of {F}rench Administrative Documents\",\n    author = \"Sebbag, Thomas  and\n      Quiniou, Solen  and\n      Stucky, Nicolas  and\n      Morin, Emmanuel\",\n    editor = \"Rambow, Owen  and\n      Wanner, Leo  and\n      Apidianaki, Marianna  and\n      Al-Khalifa, Hend  and\n      Eugenio, Barbara Di  and\n      Schockaert, Steven\",\n    booktitle = \"Proceedings of the 31st International Conference on Computational Linguistics\",\n    month = jan,\n    year = \"2025\",\n    address = \"Abu Dhabi, UAE\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.coling-main.27/\",\n    pages = \"392--406\",\n    abstract = \"In recent years, Pre-trained Language Models(PLMs) have been widely used to analyze various documents, playing a crucial role in Natural Language Processing (NLP). However, administrative texts have rarely been used in information extraction tasks, even though this resource is available as open data in many countries. Most of these texts contain many specific domain terms. Moreover, especially in France, they are unstructured because many administrations produce them without a standardized framework. Due to this fact, current language models do not process these documents correctly. In this paper, we propose AdminBERT, the first French pre-trained language models for the administr",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "1f2eebde0471c7a87cea4f956b0a30eaadfb82d9",
 "stated_evidence": "https://huggingface.co/datasets/taln-ls2n/Adminset/blob/1f2eebde0471c7a87cea4f956b0a30eaadfb82d9/README.md",
 "file_evidence": "https://huggingface.co/datasets/taln-ls2n/Adminset/tree/1f2eebde0471c7a87cea4f956b0a30eaadfb82d9",
 "card_nc": false
}