{
 "id": "SEACrowd/wit",
 "owner": "SEACrowd",
 "name": "wit",
 "downloads": 58,
 "likes": 0,
 "last_modified": "2024-06-24T13:23:33.000Z",
 "stated_licence": "cc-by-sa-3.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-sa-3.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-captioning"
 ],
 "citation": "@inproceedings{10.1145/3404835.3463257,\n    author = {Srinivasan, Krishna and Raman, Karthik and Chen, Jiecao and Bendersky, Michael and Najork, Marc},\n    title = {WIT: Wikipedia-Based Image Text Dataset for Multimodal Multilingual Machine Learning},\n    year = {2021},\n    isbn = {9781450380379},\n    publisher = {Association for Computing Machinery},\n    address = {New York, NY, USA},\n    url = {https://doi.org/10.1145/3404835.3463257},\n    doi = {10.1145/3404835.3463257},\n    booktitle = {Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval},\n    pages = {2443–2449},\n    numpages = {7},\n    keywords = {dataset, multimodal, machine learning, wikipedia, multilingual, image-text retrieval, neural networks},\n    location = {Virtual Event, Canada},\n    series = {SIGIR '21}\n}\n\n\n@article{lovenia2024seacrowd,\n    title={SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages}, \n    author={Holy Lovenia and Rahmad Mahendra and Salsabil Maulana Akbar and Lester James V. Miranda and Jennifer Santoso and Elyanah Aco and Akhdan Fadhilah and Jonibek Mansurov and Joseph Marvin Imperial and Onno P. Kampman and Joel Ruben Antony Moniz and Muhammad Ravi Shulthan Habibi and Frederikus Hudi and Railey Montalan and Ryan Ignatius and Joanito Agili Lopo and William Nixon and Börje F. Karlsson and James Jaya and Ryandito Diandaru and Yuze Gao and Patrick Amadeus and Bin Wang and Jan Christian Blaise C",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-3.0) is classified as share-alike.",
 "revision": "6fbea1a30a5e31c0da4e1369e5f8618b0589c578",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/wit/blob/6fbea1a30a5e31c0da4e1369e5f8618b0589c578/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/wit/blob/6fbea1a30a5e31c0da4e1369e5f8618b0589c578/LICENSE",
 "card_nc": false
}