beir/dbpedia

from hamu_tool.dataset import DataLoader

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

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)
    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/dbpedia')

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

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

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

@article{Hasibi2017DBpediaEntityVA,
  title={DBpedia-Entity v2: A Test Collection for Entity Search},
  author={Faegheh Hasibi and Fedor Nikolaev and Chenyan Xiong and K. Balog and S. E. Bratsberg and Alexander Kotov and J. Callan},
  journal={Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  year={2017}
}
@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",
}