irds/beir_hotpotqa

`beir/hotpotqa`数据集由`ir-datasets`包提供，包含`docs`（文档，即语料库）和`queries`（查询，即主题）两部分。其中，`docs`的数量为5,233,329，`queries`的数量为97,852。该数据集用于`beir_hotpotqa_dev`、`beir_hotpotqa_test`和`beir_hotpotqa_train`等数据集。用户可以通过`datasets`库加载该数据集，加载后的数据结构包括`doc_id`、`text`、`title`、`url`等字段。

原始信息汇总

数据集概述

数据集名称

beir/hotpotqa

数据提供者

由ir-datasets提供。

数据内容

• 文档（docs）: 数量为5,233,329。
• 查询（queries）: 数量为97,852。

数据用途

该数据集被用于以下项目：

• beir_hotpotqa_dev
• beir_hotpotqa_test
• beir_hotpotqa_train

使用示例

python from datasets import load_dataset

docs = load_dataset(irds/beir_hotpotqa, docs) for record in docs: record # {doc_id: ..., text: ..., title: ..., url: ...}

queries = load_dataset(irds/beir_hotpotqa, queries) for record in queries: record # {query_id: ..., text: ...}

引用信息

@inproceedings{Yang2018Hotpotqa, title = "{H}otpot{QA}: A Dataset for Diverse, Explainable Multi-hop Question Answering", author = "Yang, Zhilin and Qi, Peng and Zhang, Saizovich and Bengio, Yoshua and Cohen, William and Salakhutdinov, Ruslan and Manning, Christopher D.", booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing", month = oct # "-" # nov, year = "2018", address = "Brussels, Belgium", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/D18-1259", doi = "10.18653/v1/D18-1259", pages = "2369--2380" } @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", }