beir/nfcorpus

from hamu_tool.dataset import DataLoader

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

for doc in loader.get_docs():
    print(doc.id, doc.text, doc.title, doc.url)
    break

for query in loader.get_queries():
    print(query.id, query.text, query.url)
    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/nfcorpus')

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

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

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

@inproceedings{Boteva2016Nfcorpus,
  title = "A Full-Text Learning to Rank Dataset for Medical Information Retrieval",
  author = "Vera Boteva and Demian Gholipour and Artem Sokolov and Stefan Riezler",
  booktitle = "Proceedings of the European Conference on Information Retrieval ({ECIR})",
  location = "Padova, Italy",
  publisher = "Springer",
  year = 2016
}
@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",
}