{
 "id": "SEACrowd/identic",
 "owner": "SEACrowd",
 "name": "identic",
 "downloads": 67,
 "likes": 0,
 "last_modified": "2024-06-24T13:25:51.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-nc-sa-3.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "machine-translation",
  "pos-tagging"
 ],
 "citation": "@inproceedings{larasati-2012-identic,\n    title = \"{IDENTIC} Corpus: Morphologically Enriched {I}ndonesian-{E}nglish Parallel Corpus\",\n    author = \"Larasati, Septina Dian\",\n    booktitle = \"Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)\",\n    month = may,\n    year = \"2012\",\n    address = \"Istanbul, Turkey\",\n    publisher = \"European Language Resources Association (ELRA)\",\n    url = \"http://www.lrec-conf.org/proceedings/lrec2012/pdf/644_Paper.pdf\",\n    pages = \"902--906\",\n    abstract = \"This paper describes the creation process of an Indonesian-English parallel corpus (IDENTIC).\n    The corpus contains 45,000 sentences collected from different sources in different genres.\n    Several manual text preprocessing tasks, such as alignment and spelling correction, are applied to the corpus\n    to assure its quality. We also apply language specific text processing such as tokenization on both sides and\n    clitic normalization on the Indonesian side. The corpus is available in two different formats: ‘plain',\n    stored in text format and ‘morphologically enriched', stored in CoNLL format. Some parts of the corpus are\n    publicly available at the IDENTIC homepage.\",\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 ",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "c911521e01cceb90e9ec7336e7f99ad3e0ddd588",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/identic/blob/c911521e01cceb90e9ec7336e7f99ad3e0ddd588/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/identic/blob/c911521e01cceb90e9ec7336e7f99ad3e0ddd588/LICENSE",
 "card_nc": false
}