{
 "id": "SEACrowd/cc_aligned_sent",
 "owner": "SEACrowd",
 "name": "cc_aligned_sent",
 "downloads": 38,
 "likes": 0,
 "last_modified": "2024-06-24T13:25:30.000Z",
 "stated_licence": "unknown",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "machine-translation"
 ],
 "citation": "@inproceedings{chaudhary-etal-2019-low,\n    title = \"Low-Resource Corpus Filtering Using Multilingual Sentence Embeddings\",\n    author = \"Chaudhary, Vishrav  and\n      Tang, Yuqing  and\n      Guzm{\\'a}n, Francisco  and\n      Schwenk, Holger  and\n      Koehn, Philipp\",\n    editor = \"Bojar, Ond{\\v{r}}ej  and\n      Chatterjee, Rajen  and\n      Federmann, Christian  and\n      Fishel, Mark  and\n      Graham, Yvette  and\n      Haddow, Barry  and\n      Huck, Matthias  and\n      Yepes, Antonio Jimeno  and\n      Koehn, Philipp  and\n      Martins, Andr{\\'e}  and\n      Monz, Christof  and\n      Negri, Matteo  and\n      N{\\'e}v{\\'e}ol, Aur{\\'e}lie  and\n      Neves, Mariana  and\n      Post, Matt  and\n      Turchi, Marco  and\n      Verspoor, Karin\",\n    booktitle = \"Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)\",\n    month = aug,\n    year = \"2019\",\n    address = \"Florence, Italy\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/W19-5435\",\n    doi = \"10.18653/v1/W19-5435\",\n    pages = \"261--266\",\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 Mu",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "2ec10a674cba008ddc3b0a9ca7b61525356f84e7",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/cc_aligned_sent/blob/2ec10a674cba008ddc3b0a9ca7b61525356f84e7/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/cc_aligned_sent/blob/2ec10a674cba008ddc3b0a9ca7b61525356f84e7/LICENSE",
 "card_nc": false
}