{
 "id": "irds/nyt_wksup_train",
 "owner": "irds",
 "name": "nyt_wksup_train",
 "downloads": 7,
 "likes": 0,
 "last_modified": "2023-01-05T03:48:16.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "irds/nyt",
   "licence": null,
   "found": true,
   "evidence": "https://huggingface.co/datasets/irds/nyt/blob/1edb0703e2cd3fd18745d67a7bd9fd6e3cb8d859/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "@inproceedings{MacAvaney2019Wksup,\n  author = {MacAvaney, Sean and Yates, Andrew and Hui, Kai and Frieder, Ophir},\n  title = {Content-Based Weak Supervision for Ad-Hoc Re-Ranking},\n  booktitle = {SIGIR},\n  year = {2019}\n}\n@article{Sandhaus2008Nyt,\n  title={The new york times annotated corpus},\n  author={Sandhaus, Evan},\n  journal={Linguistic Data Consortium, Philadelphia},\n  volume={6},\n  number={12},\n  pages={e26752},\n  year={2008}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "452d6a5f6e151dc2c22b9ad4eaaae5fafe216ebc",
 "stated_evidence": "https://huggingface.co/datasets/irds/nyt_wksup_train/blob/452d6a5f6e151dc2c22b9ad4eaaae5fafe216ebc/README.md",
 "file_evidence": "https://huggingface.co/datasets/irds/nyt_wksup_train/tree/452d6a5f6e151dc2c22b9ad4eaaae5fafe216ebc",
 "card_nc": false
}