instruct_med_dataset.hf/dataset_info.json

{
  "citation": "@article{Cohan_2018,\n   title={A Discourse-Aware Attention Model for Abstractive Summarization of\n            Long Documents},\n   url={http://dx.doi.org/10.18653/v1/n18-2097},\n   DOI={10.18653/v1/n18-2097},\n   journal={Proceedings of the 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 2 (Short Papers)},\n   publisher={Association for Computational Linguistics},\n   author={Cohan, Arman and Dernoncourt, Franck and Kim, Doo Soon and Bui, Trung and Kim, Seokhwan and Chang, Walter and Goharian, Nazli},\n   year={2018}\n}",
  "description": "Scientific papers datasets contains two sets of long and structured documents.\nThe datasets are obtained from ArXiv and PubMed OpenAccess repositories.\n\nBoth \"arxiv\" and \"pubmed\" have two features:\n  - article: the body of the document, pagragraphs seperated by \"/n\".\n  - abstract: the abstract of the document, pagragraphs seperated by \"/n\".\n  - section_names: titles of sections, seperated by \"/n\".",
  "features": {
    "text": {
      "dtype": "string",
      "_type": "Value"
    }
  },
  "homepage": "https://github.com/armancohan/long-summarization",
  "license": ""
}