ellamind/wikipedia-2023-11-retrieval-multilingual-qrels

---
dataset_info:
- config_name: bg
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 709541
num_examples: 13500
download_size: 122515
dataset_size: 709541
- config_name: bn
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 717171
num_examples: 13500
download_size: 123704
dataset_size: 717171
- config_name: cs
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 712839
num_examples: 13500
download_size: 123503
dataset_size: 712839
- config_name: da
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 709126
num_examples: 13500
download_size: 122777
dataset_size: 709126
- config_name: de
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 725751
num_examples: 13500
download_size: 125662
dataset_size: 725751
- config_name: en
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 739207
num_examples: 13500
download_size: 127940
dataset_size: 739207
- config_name: fa
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 715293
num_examples: 13500
download_size: 124099
dataset_size: 715293
- config_name: fi
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 707024
num_examples: 13500
download_size: 122735
dataset_size: 707024
- config_name: hi
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 710679
num_examples: 13500
download_size: 123514
dataset_size: 710679
- config_name: it
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 730665
num_examples: 13500
download_size: 126009
dataset_size: 730665
- config_name: nl
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 712094
num_examples: 13500
download_size: 123642
dataset_size: 712094
- config_name: 'no'
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 711568
num_examples: 13500
download_size: 123307
dataset_size: 711568
- config_name: pt
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 718008
num_examples: 13500
download_size: 124651
dataset_size: 718008
- config_name: ro
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 718107
num_examples: 13500
download_size: 124512
dataset_size: 718107
- config_name: sr
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 718940
num_examples: 13500
download_size: 124008
dataset_size: 718940
- config_name: sv
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float32
splits:
- name: test
num_bytes: 707631
num_examples: 13500
download_size: 122899
dataset_size: 707631
configs:
- config_name: bg
data_files:
- split: test
path: bg/test-*
- config_name: bn
data_files:
- split: test
path: bn/test-*
- config_name: cs
data_files:
- split: test
path: cs/test-*
- config_name: da
data_files:
- split: test
path: da/test-*
- config_name: de
data_files:
- split: test
path: de/test-*
- config_name: en
data_files:
- split: test
path: en/test-*
- config_name: fa
data_files:
- split: test
path: fa/test-*
- config_name: fi
data_files:
- split: test
path: fi/test-*
- config_name: hi
data_files:
- split: test
path: hi/test-*
- config_name: it
data_files:
- split: test
path: it/test-*
- config_name: nl
data_files:
- split: test
path: nl/test-*
- config_name: 'no'
data_files:
- split: test
path: no/test-*
- config_name: pt
data_files:
- split: test
path: pt/test-*
- config_name: ro
data_files:
- split: test
path: ro/test-*
- config_name: sr
data_files:
- split: test
path: sr/test-*
- config_name: sv
data_files:
- split: test
path: sv/test-*
---

原始信息汇总

数据集概述

数据集配置

• config_name: 数据集配置名称，包括bg、bn、cs、da、de、en、fa、fi、hi、it、nl、no、pt、ro、sr、sv等。
• features: 数据集特征，每个配置包含以下特征：
  • query-id: 数据类型为string。
  • corpus-id: 数据类型为string。
  • score: 数据类型为float32。

数据集分割

• splits: 每个配置的数据集分割信息，仅包含test分割。
  • num_bytes: 数据大小，单位为字节。
  • num_examples: 示例数量，固定为13500。

数据集大小

• download_size: 下载大小，单位为字节。
• dataset_size: 数据集总大小，单位为字节。

数据文件路径

• data_files: 每个配置的数据文件路径，格式为{config_name}/test-*。