from hamu_tool.dataset import DataLoader
loader = DataLoader.load('beir/fever')
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{Thorne2018Fever,
title = "{FEVER}: a Large-scale Dataset for Fact Extraction and {VER}ification",
author = "Thorne, James and
Vlachos, Andreas and
Christodoulopoulos, Christos and
Mittal, Arpit",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/N18-1074",
doi = "10.18653/v1/N18-1074",
pages = "809--819"
}
@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",
}