mFollowIR-cross-lingual-parquet

# mFollowIR-cross-lingual-parquet

This is a parquet version of the mFollowIR cross-lingual dataset that can be loaded directly with `load_dataset()`. The original dataset can be found at [jhu-clsp/mFollowIR-cross-lingual](https://huggingface.co/datasets/jhu-clsp/mFollowIR-cross-lingual).

## Dataset Structure

The dataset contains the following configurations for each target language (fas, rus, zho):

### Configurations
- `qrels_og_[lang]`: Original relevance judgments (test split)
- `qrels_changed_[lang]`: Modified relevance judgments (test split)
- `corpus_[lang]`: Document collection
- `queries_[lang]`: Query set with instructions
- `top_ranked_[lang]`: Top ranked documents

## Usage

```python
from datasets import load_dataset

# Load a specific configuration
dataset = load_dataset("jhu-clsp/mFollowIR-cross-lingual-parquet", "queries_fas") # or any other config

# Load multiple configurations
dataset = load_dataset("jhu-clsp/mFollowIR-cross-lingual-parquet",
["queries_fas", "corpus_fas"])
```

## Citation

```bibtex
@article{weller2024mfollowir,
title="mFollowIR: a Multilingual Benchmark for Instruction Following in Information Retrieval",
author="Weller, Orion and Chang, Benjamin and Yang, Eugene and Yarmohammadi, Mahsa and Barham, Sam and MacAvaney, Sean and Cohan, Arman and Soldaini, Luca and Van Durme, Benjamin and Lawrie, Dawn",
journal="arXiv preprint TODO",
year="2024"
}
```

# mFollowIR-cross-lingual-parquet

本数据集为mFollowIR跨语言数据集的Parquet（帕科列存储文件格式）版本，可直接通过`load_dataset()`函数加载。原始数据集可在[https://huggingface.co/datasets/jhu-clsp/mFollowIR-cross-lingual](https://huggingface.co/datasets/jhu-clsp/mFollowIR-cross-lingual)获取。

## 数据集结构

本数据集针对以下目标语言（波斯语`fas`、俄语`rus`、中文`zho`）提供如下配置项：

### 配置项

- `qrels_og_[lang]`：原始相关性标注（测试集划分）
- `qrels_changed_[lang]`：修改后的相关性标注（测试集划分）
- `corpus_[lang]`：文档集合
- `queries_[lang]`：带有检索指令的查询集合
- `top_ranked_[lang]`：Top排序文档

## 使用方法

python
from datasets import load_dataset

# 加载指定配置项
dataset = load_dataset("jhu-clsp/mFollowIR-cross-lingual-parquet", "queries_fas") # 或其他任意配置项

# 加载多个配置项
dataset = load_dataset("jhu-clsp/mFollowIR-cross-lingual-parquet", ["queries_fas", "corpus_fas"])

## 引用格式

bibtex
@article{weller2024mfollowir,
title="mFollowIR: a Multilingual Benchmark for Instruction Following in Information Retrieval",
author="Weller, Orion and Chang, Benjamin and Yang, Eugene and Yarmohammadi, Mahsa and Barham, Sam and MacAvaney, Sean and Cohan, Arman and Soldaini, Luca and Van Durme, Benjamin and Lawrie, Dawn",
journal="arXiv preprint TODO",
year="2024"
}

搜集汇总

背景与挑战

背景概述

该数据集是mFollowIR跨语言信息检索基准的Parquet格式版本，支持波斯语、俄语和中文，包含原始和修改的相关性判断、文档集、查询集及顶级排名文档等多种配置。它可直接通过load_dataset()函数加载，便于使用。