{
 "id": "MichaelR207/MultiSimV2",
 "owner": "MichaelR207",
 "name": "MultiSimV2",
 "downloads": 1023,
 "likes": 5,
 "last_modified": "2024-10-23T00:02:09.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "summarization",
  "text2text-generation",
  "text-generation"
 ],
 "citation": "@inproceedings{ryan-etal-2023-revisiting,\n    title = \"Revisiting non-{E}nglish Text Simplification: A Unified Multilingual Benchmark\",\n    author = \"Ryan, Michael  and\n      Naous, Tarek  and\n      Xu, Wei\",\n    booktitle = \"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\",\n    month = jul,\n    year = \"2023\",\n    address = \"Toronto, Canada\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.acl-long.269\",\n    pages = \"4898--4927\",\n    abstract = \"Recent advancements in high-quality, large-scale English resources have pushed the frontier of English Automatic Text Simplification (ATS) research. However, less work has been done on multilingual text simplification due to the lack of a diverse evaluation benchmark that covers complex-simple sentence pairs in many languages. This paper introduces the MultiSim benchmark, a collection of 27 resources in 12 distinct languages containing over 1.7 million complex-simple sentence pairs. This benchmark will encourage research in developing more effective multilingual text simplification models and evaluation metrics. Our experiments using MultiSim with pre-trained multilingual language models reveal exciting performance improvements from multilingual training in non-English settings. We observe strong performance from Russian in zero-shot cross-lingual transfer to low-resource languages. We further show that few-shot prompt",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "03aaf798070c845ce8e8980dc20e92f079028611",
 "stated_evidence": "https://huggingface.co/datasets/MichaelR207/MultiSimV2/blob/03aaf798070c845ce8e8980dc20e92f079028611/README.md",
 "file_evidence": "https://huggingface.co/datasets/MichaelR207/MultiSimV2/tree/03aaf798070c845ce8e8980dc20e92f079028611",
 "card_nc": false
}