{
 "id": "expertai/BUSTER",
 "owner": "expertai",
 "name": "BUSTER",
 "downloads": 816,
 "likes": 5,
 "last_modified": "2024-07-04T16:09:48.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "token-classification"
 ],
 "citation": "@inproceedings{zugarini-etal-2023-buster,\n    title = \"{BUSTER}: a {``}{BUS}iness Transaction Entity Recognition{''} dataset\",\n    author = \"Zugarini, Andrea  and\n      Zamai, Andrew  and\n      Ernandes, Marco  and\n      Rigutini, Leonardo\",\n    editor = \"Wang, Mingxuan  and\n      Zitouni, Imed\",\n    booktitle = \"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track\",\n    month = dec,\n    year = \"2023\",\n    address = \"Singapore\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.emnlp-industry.57\",\n    doi = \"10.18653/v1/2023.emnlp-industry.57\",\n    pages = \"605--611\",\n    abstract = \"Albeit Natural Language Processing has seen major breakthroughs in the last few years, transferring such advances into real-world business cases can be challenging. One of the reasons resides in the displacement between popular benchmarks and actual data. Lack of supervision, unbalanced classes, noisy data and long documents often affect real problems in vertical domains such as finance, law and health. To support industry-oriented research, we present BUSTER, a BUSiness Transaction Entity Recognition dataset. The dataset consists of 3779 manually annotated documents on financial transactions. We establish several baselines exploiting both general-purpose and domain-specific language models. The best performing model is also used to automatically annotate 6196 documents, which we release as an ad",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "a70c91d81f0c6db4acff827e5cebaff552883dd5",
 "stated_evidence": "https://huggingface.co/datasets/expertai/BUSTER/blob/a70c91d81f0c6db4acff827e5cebaff552883dd5/README.md",
 "file_evidence": "https://huggingface.co/datasets/expertai/BUSTER/tree/a70c91d81f0c6db4acff827e5cebaff552883dd5",
 "card_nc": false
}