{
 "id": "AmazonScience/MultilingualMultiModalClassification",
 "owner": "AmazonScience",
 "name": "MultilingualMultiModalClassification",
 "downloads": 55913,
 "likes": 8,
 "last_modified": "2024-12-06T14:00:39.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{fujinuma-etal-2023-multi,\n    title = \"A Multi-Modal Multilingual Benchmark for Document Image Classification\",\n    author = \"Fujinuma, Yoshinari  and\n      Varia, Siddharth  and\n      Sankaran, Nishant  and\n      Appalaraju, Srikar  and\n      Min, Bonan  and\n      Vyas, Yogarshi\",\n    editor = \"Bouamor, Houda  and\n      Pino, Juan  and\n      Bali, Kalika\",\n    booktitle = \"Findings of the Association for Computational Linguistics: EMNLP 2023\",\n    month = dec,\n    year = \"2023\",\n    address = \"Singapore\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.findings-emnlp.958\",\n    doi = \"10.18653/v1/2023.findings-emnlp.958\",\n    pages = \"14361--14376\",\n    abstract = \"Document image classification is different from plain-text document classification and consists of classifying a document by understanding the content and structure of documents such as forms, emails, and other such documents. We show that the only existing dataset for this task (Lewis et al., 2006) has several limitations and we introduce two newly curated multilingual datasets WIKI-DOC and MULTIEURLEX-DOC that overcome these limitations. We further undertake a comprehensive study of popular visually-rich document understanding or Document AI models in previously untested setting in document image classification such as 1) multi-label classification, and 2) zero-shot cross-lingual transfer setup. Experimental results show limitations of multiling",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive."
}