beir/scidocs

from hamu_tool.dataset import DataLoader

loader = DataLoader.load('beir/scidocs')

for doc in loader.get_docs():
    print(doc.id, doc.text, doc.title, doc.authors, doc.year, doc.cited_by, doc.references)
    break

for query in loader.get_queries():
    print(query.id, query.text, query.authors, query.year, query.cited_by, query.references)
    break

for qrel in loader.get_qrels('[mode]'):
    print(qrel.qid, qrel.did, qrel.score)
    break

from hamu_tool.dataset import DataLoader

loader = DataLoader.load('beir/scidocs')

doc = loader.get_doc('[did]')
print(doc)

query = loader.get_query('[qid]')
print(query)

qrel = loader.get_qrel('[mode]', '[qid]')
print(qrel)

@inproceedings{Cohan2020Scidocs,
    title = "{SPECTER}: Document-level Representation Learning using Citation-informed Transformers",
    author = "Cohan, Arman and Feldman, Sergey and Beltagy, Iz  and Downey, Doug  and Weld, Daniel",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-main.207",
    doi = "10.18653/v1/2020.acl-main.207",
    pages = "2270--2282"
}
@article{Thakur2021Beir,
  title = "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models",
  author = "Thakur, Nandan and Reimers, Nils and Rücklé, Andreas and Srivastava, Abhishek and Gurevych, Iryna", 
  journal = "arXiv preprint arXiv:2104.08663",
  month = "4",
  year = "2021",
  url = "https://arxiv.org/abs/2104.08663",
}