{
 "id": "jaredfern/codah",
 "owner": "jaredfern",
 "name": "codah",
 "downloads": 26679,
 "likes": 6,
 "last_modified": "2024-01-19T10:16:56.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering"
 ],
 "citation": "@inproceedings{chen-etal-2019-codah,\n    title = \"{CODAH}: An Adversarially-Authored Question Answering Dataset for Common Sense\",\n    author = \"Chen, Michael  and\n      D{'}Arcy, Mike  and\n      Liu, Alisa  and\n      Fernandez, Jared  and\n      Downey, Doug\",\n    editor = \"Rogers, Anna  and\n      Drozd, Aleksandr  and\n      Rumshisky, Anna  and\n      Goldberg, Yoav\",\n    booktitle = \"Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for {NLP}\",\n    month = jun,\n    year = \"2019\",\n    address = \"Minneapolis, USA\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/W19-2008\",\n    doi = \"10.18653/v1/W19-2008\",\n    pages = \"63--69\",\n    abstract = \"Commonsense reasoning is a critical AI capability, but it is difficult to construct challenging datasets that test common sense. Recent neural question answering systems, based on large pre-trained models of language, have already achieved near-human-level performance on commonsense knowledge benchmarks. These systems do not possess human-level common sense, but are able to exploit limitations of the datasets to achieve human-level scores. We introduce the CODAH dataset, an adversarially-constructed evaluation dataset for testing common sense. CODAH forms a challenging extension to the recently-proposed SWAG dataset, which tests commonsense knowledge using sentence-completion questions that describe situations observed in video. To produce a more difficult dataset,",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive."
}