irds/beir_arguana

`beir/arguana`数据集由`ir-datasets`包提供，包含三个主要部分：`docs`（文档，即语料库，共8,674条）、`queries`（查询，即主题，共1,406条）和`qrels`（相关性评估，共1,406条）。该数据集用于文本检索任务，用户可以通过`datasets`库加载并使用这些数据。

The `beir/arguana` dataset is provided by the `ir-datasets` package, and it comprises three primary components: `docs` (the corpus, containing 8,674 documents in total), `queries` (the topics, with 1,406 queries in total), and `qrels` (the relevance assessments, with 1,406 entries in total). This dataset is designed for text retrieval tasks, and users can load and utilize these data via the `datasets` library.

原始信息汇总

数据集卡片 for beir/arguana

数据集概述

beir/arguana 数据集由 ir-datasets 包提供。

数据内容

该数据集包含以下内容：

• docs（文档，即语料库）；数量=8,674
• queries（即主题）；数量=1,406
• qrels（相关性评估）；数量=1,406

使用方法

python from datasets import load_dataset

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

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

qrels = load_dataset(irds/beir_arguana, qrels) for record in qrels: record # {query_id: ..., doc_id: ..., relevance: ..., iteration: ...}

引用信息

@inproceedings{Wachsmuth2018Arguana, author = "Wachsmuth, Henning and Syed, Shahbaz and Stein, Benno", title = "Retrieval of the Best Counterargument without Prior Topic Knowledge", booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", year = "2018", publisher = "Association for Computational Linguistics", location = "Melbourne, Australia", pages = "241--251", url = "http://aclweb.org/anthology/P18-1023" } @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", }