from hamu_tool.dataset import DataLoader
loader = DataLoader.load('beir/scifact')
for doc in loader.get_docs():
print(doc.id, doc.text, doc.title)
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
@inproceedings{Wadden2020Scifact,
title = "Fact or Fiction: Verifying Scientific Claims",
author = "Wadden, David and Lin, Shanchuan and Lo, Kyle and Wang, Lucy Lu and an Zuylen, Madeleine and Cohan, Arman and Hajishirzi, Hannaneh",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.emnlp-main.609",
doi = "10.18653/v1/2020.emnlp-main.609",
pages = "7534--7550"
}
@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",
}