{
 "id": "rogerdehe/xfund",
 "owner": "rogerdehe",
 "name": "xfund",
 "downloads": 53,
 "likes": 2,
 "last_modified": "2022-10-12T12:42:35.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "``` latex\n@inproceedings{xu-etal-2022-xfund,\n    title = \"{XFUND}: A Benchmark Dataset for Multilingual Visually Rich Form Understanding\",\n    author = \"Xu, Yiheng  and\n      Lv, Tengchao  and\n      Cui, Lei  and\n      Wang, Guoxin  and\n      Lu, Yijuan  and\n      Florencio, Dinei  and\n      Zhang, Cha  and\n      Wei, Furu\",\n    booktitle = \"Findings of the Association for Computational Linguistics: ACL 2022\",\n    month = may,\n    year = \"2022\",\n    address = \"Dublin, Ireland\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2022.findings-acl.253\",\n    doi = \"10.18653/v1/2022.findings-acl.253\",\n    pages = \"3214--3224\",\n    abstract = \"Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. However, the existed research work has focused only on the English domain while neglecting the importance of multilingual generalization. In this paper, we introduce a human-annotated multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese). Meanwhile, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually rich document understanding. Experimental result",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "e11e9d7b5b84d5b50b12de433ba7823ef85ca40c",
 "stated_evidence": "https://huggingface.co/datasets/rogerdehe/xfund/blob/e11e9d7b5b84d5b50b12de433ba7823ef85ca40c/README.md",
 "file_evidence": "https://huggingface.co/datasets/rogerdehe/xfund/tree/e11e9d7b5b84d5b50b12de433ba7823ef85ca40c",
 "card_nc": false
}