beir/signal1m

from hamu_tool.dataset import DataLoader

loader = DataLoader.load('beir/signal1m')

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

for query in loader.get_queries():
    print(query.id, query.text)
    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/signal1m')

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

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

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

@inproceedings{Signal1M2016,
  author = {David Corney and Dyaa Albakour and Miguel Martinez and Samir Moussa},
  title = {What do a Million News Articles Look like?},
  booktitle = {Proceedings of the First International Workshop on Recent Trends in News Information Retrieval co-located with 38th European Conference on Information Retrieval {(ECIR} 2016), Padua, Italy, March 20, 2016.},
  pages = {42--47},
  year = {2016},
  url = {http://ceur-ws.org/Vol-1568/paper8.pdf}
}
@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",
}