irds/lotte_science_test_search

`lotte/science/test/search`数据集由`ir-datasets`包提供，包含617个查询（topics）和1,738个相关评估（relevance assessments）。文档部分需要使用`irds/lotte_science_test`数据集。

原始信息汇总

数据集概述

数据集名称

lotte/science/test/search

数据集来源

• 源数据集：irds/lotte_science_test

数据集内容

• queries（查询）：617条
• qrels（相关性评估）：1,738条
• docs（文档）：使用irds/lotte_science_test数据集

数据集用途

• 用于文本检索任务

数据集加载示例

python from datasets import load_dataset

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

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

引用信息

@article{Santhanam2021ColBERTv2, title = "ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction", author = "Keshav Santhanam and Omar Khattab and Jon Saad-Falcon and Christopher Potts and Matei Zaharia", journal= "arXiv preprint arXiv:2112.01488", year = "2021", url = "https://arxiv.org/abs/2112.01488" }