irds/mr-tydi_bn_test

`mr-tydi/bn/test`数据集由`ir-datasets`包提供，主要用于文本检索任务。该数据集包含111个查询（即主题）和130个相关性评估（qrels）。文档部分需要从`irds/mr-tydi_bn`数据集中获取。使用示例展示了如何通过`datasets`库加载查询和相关性评估数据。

The `mr-tydi/bn/test` dataset, provided by the `ir-datasets` package, is primarily designed for text retrieval tasks. It contains 111 queries (also known as topics) and 130 relevance judgments (qrels). The document collection of this dataset needs to be obtained from the `irds/mr-tydi_bn` dataset. A usage example demonstrates how to load the query and relevance judgment data via the `datasets` library.

原始信息汇总

数据集概述

数据集名称

mr-tydi/bn/test

数据来源

• 源数据集: irds/mr-tydi_bn

数据内容

• queries: 查询（即主题），数量为111个。
• qrels: 相关性评估，数量为130个。
• docs: 文档数据，使用irds/mr-tydi_bn数据集。

使用示例

python from datasets import load_dataset

加载查询数据

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

加载相关性评估数据

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

引用信息

@article{Zhang2021MrTyDi, title={{Mr. TyDi}: A Multi-lingual Benchmark for Dense Retrieval}, author={Xinyu Zhang and Xueguang Ma and Peng Shi and Jimmy Lin}, year={2021}, journal={arXiv:2108.08787}, } @article{Clark2020TyDiQa, title={{TyDi QA}: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages}, author={Jonathan H. Clark and Eunsol Choi and Michael Collins and Dan Garrette and Tom Kwiatkowski and Vitaly Nikolaev and Jennimaria Palomaki}, year={2020}, journal={Transactions of the Association for Computational Linguistics} }