{
 "id": "INK-USC/xcsr",
 "owner": "INK-USC",
 "name": "xcsr",
 "downloads": 2586,
 "likes": 8,
 "last_modified": "2024-01-04T17:03:17.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "codah",
   "licence": "odc-by",
   "found": true,
   "evidence": "https://huggingface.co/datasets/jaredfern/codah/blob/4b0e0e7f33b3ae8cd8e69bcdfa09af9611d8f3bd/README.md"
  },
  {
   "id": "commonsense_qa",
   "licence": "mit",
   "found": true,
   "evidence": "https://huggingface.co/datasets/tau/commonsense_qa/blob/94630fe30dad47192a8546eb75f094926d47e155/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "question-answering"
 ],
 "citation": "```\n# X-CSR\n@inproceedings{lin-etal-2021-common,\n    title = \"Common Sense Beyond {E}nglish: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning\",\n    author = \"Lin, Bill Yuchen  and\n      Lee, Seyeon  and\n      Qiao, Xiaoyang  and\n      Ren, Xiang\",\n    booktitle = \"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)\",\n    month = aug,\n    year = \"2021\",\n    address = \"Online\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2021.acl-long.102\",\n    doi = \"10.18653/v1/2021.acl-long.102\",\n    pages = \"1274--1287\",\n    abstract = \"Commonsense reasoning research has so far been limited to English. We aim to evaluate and improve popular multilingual language models (ML-LMs) to help advance commonsense reasoning (CSR) beyond English. We collect the Mickey corpus, consisting of 561k sentences in 11 different languages, which can be used for analyzing and improving ML-LMs. We propose Mickey Probe, a language-general probing task for fairly evaluating the common sense of popular ML-LMs across different languages. In addition, we also create two new datasets, X-CSQA and X-CODAH, by translating their English versions to 14 other languages, so that we can evaluate popular ML-LMs for cross-lingual commonsense reasoning. To improve the performance beyond English, we propose a simp",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "f691f311a11f84773a899e9bfc7da2bae51b0b02",
 "stated_evidence": "https://huggingface.co/datasets/INK-USC/xcsr/blob/f691f311a11f84773a899e9bfc7da2bae51b0b02/README.md",
 "file_evidence": "https://huggingface.co/datasets/INK-USC/xcsr/tree/f691f311a11f84773a899e9bfc7da2bae51b0b02",
 "card_nc": false
}