{
 "id": "larrylawl/multilexnorm",
 "owner": "larrylawl",
 "name": "multilexnorm",
 "downloads": 127,
 "likes": 1,
 "last_modified": "2023-05-05T08:17:00.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@inproceedings{van-der-goot-etal-2021-multilexnorm,\n    title = \"{M}ulti{L}ex{N}orm: A Shared Task on Multilingual Lexical Normalization\",\n    author = {van der Goot, Rob  and\n      Ramponi, Alan  and\n      Zubiaga, Arkaitz  and\n      Plank, Barbara  and\n      Muller, Benjamin  and\n      San Vicente Roncal, I{\\~n}aki  and\n      Ljube{\\v{s}}i{\\'c}, Nikola  and\n      {\\c{C}}etino{\\u{g}}lu, {\\\"O}zlem  and\n      Mahendra, Rahmad  and\n      {\\c{C}}olako{\\u{g}}lu, Talha  and\n      Baldwin, Timothy  and\n      Caselli, Tommaso  and\n      Sidorenko, Wladimir},\n    booktitle = \"Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)\",\n    month = nov,\n    year = \"2021\",\n    address = \"Online\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2021.wnut-1.55\",\n    doi = \"10.18653/v1/2021.wnut-1.55\",\n    pages = \"493--509\",\n    abstract = \"Lexical normalization is the task of transforming an utterance into its standardized form. This task is beneficial for downstream analysis, as it provides a way to harmonize (often spontaneous) linguistic variation. Such variation is typical for social media on which information is shared in a multitude of ways, including diverse languages and code-switching. Since the seminal work of Han and Baldwin (2011) a decade ago, lexical normalization has attracted attention in English and multiple other languages. However, there exists a lack of a common benchmark for comparison of systems ac",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "b4c95cd95c9ce981a1fa12de9277fe28e3431323",
 "stated_evidence": "https://huggingface.co/datasets/larrylawl/multilexnorm/blob/b4c95cd95c9ce981a1fa12de9277fe28e3431323/README.md",
 "file_evidence": "https://huggingface.co/datasets/larrylawl/multilexnorm/tree/b4c95cd95c9ce981a1fa12de9277fe28e3431323",
 "card_nc": false
}