{
 "id": "GEM/totto",
 "owner": "GEM",
 "name": "totto",
 "downloads": 476,
 "likes": 2,
 "last_modified": "2022-10-24T15:30:32.000Z",
 "stated_licence": "cc-by-sa-3.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "table-to-text"
 ],
 "citation": "@inproceedings{parikh-etal-2020-totto,\n    title = \"{ToTTo}: A Controlled Table-To-Text Generation Dataset\",\n    author = \"Parikh, Ankur  and\n      Wang, Xuezhi  and\n      Gehrmann, Sebastian  and\n      Faruqui, Manaal  and\n      Dhingra, Bhuwan  and\n      Yang, Diyi  and\n      Das, Dipanjan\",\n    booktitle = \"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)\",\n    month = nov,\n    year = \"2020\",\n    address = \"Online\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2020.emnlp-main.89\",\n    doi = \"10.18653/v1/2020.emnlp-main.89\",\n    pages = \"1173--1186\",\n    abstract = \"We present ToTTo, an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description. To obtain generated targets that are natural but also faithful to the source table, we introduce a dataset construction process where annotators directly revise existing candidate sentences from Wikipedia. We present systematic analyses of our dataset and annotation process as well as results achieved by several state-of-the-art baselines. While usually fluent, existing methods often hallucinate phrases that are not supported by the table, suggesting that this dataset can serve as a useful research benchmark for high-precision conditional text generation.\",\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-3.0) is classified as share-alike.",
 "revision": "5e745cedfd0050cc18aa143e5325d03061941d7d",
 "stated_evidence": "https://huggingface.co/datasets/GEM/totto/blob/5e745cedfd0050cc18aa143e5325d03061941d7d/README.md",
 "file_evidence": "https://huggingface.co/datasets/GEM/totto/tree/5e745cedfd0050cc18aa143e5325d03061941d7d",
 "card_nc": false
}