UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB
收藏Hugging Face2026-04-16 更新2026-04-26 收录
下载链接:
https://hf-mirror.com/datasets/UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB
下载链接
链接失效反馈官方服务:
资源简介:
---
configs:
- config_name: corpus
data_files:
- path: corpus/corpus-*
split: corpus
- config_name: default
data_files:
- split: test
path: data/test-*
- config_name: queries_de_en
data_files:
- path: queries_de_en/train-*
split: train
- config_name: queries_es_en
data_files:
- path: queries_es_en/train-*
split: train
- config_name: queries_fr_en
data_files:
- path: queries_fr_en/train-*
split: train
- config_name: queries_it_en
data_files:
- path: queries_it_en/train-*
split: train
- config_name: queries_ja_en
data_files:
- path: queries_ja_en/train-*
split: train
- config_name: queries_ko_en
data_files:
- path: queries_ko_en/train-*
split: train
- config_name: queries_nl_en
data_files:
- path: queries_nl_en/train-*
split: train
- config_name: queries_pt_en
data_files:
- path: queries_pt_en/train-*
split: train
- config_name: queries_zh_en
data_files:
- path: queries_zh_en/train-*
split: train
dataset_info:
- config_name: corpus
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: corpus
num_examples: 303732
- config_name: default
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: float64
splits:
- name: test
num_bytes: 161729
num_examples: 2849
download_size: 50929
dataset_size: 161729
- config_name: queries_de_en
features:
- name: _id
dtype: string
- name: text
dtype: string
splits:
- name: train
num_examples: 49
- config_name: queries_es_en
features:
- name: _id
dtype: string
- name: text
dtype: string
splits:
- name: train
num_examples: 49
- config_name: queries_fr_en
features:
- name: _id
dtype: string
- name: text
dtype: string
splits:
- name: train
num_examples: 49
- config_name: queries_it_en
features:
- name: _id
dtype: string
- name: text
dtype: string
splits:
- name: train
num_examples: 49
- config_name: queries_ja_en
features:
- name: _id
dtype: string
- name: text
dtype: string
- name: metadata
struct:
- name: description
dtype: string
- name: narrative
dtype: string
splits:
- name: train
num_examples: 49
- config_name: queries_ko_en
features:
- name: _id
dtype: string
- name: text
dtype: string
splits:
- name: train
num_examples: 49
- config_name: queries_nl_en
features:
- name: _id
dtype: string
- name: text
dtype: string
splits:
- name: train
num_examples: 49
- config_name: queries_pt_en
features:
- name: _id
dtype: string
- name: text
dtype: string
splits:
- name: train
num_examples: 49
- config_name: queries_zh_en
features:
- name: _id
dtype: string
- name: text
dtype: string
- name: metadata
struct:
- name: description
dtype: string
- name: narrative
dtype: string
splits:
- name: train
num_examples: 49
license: mit
language:
- en
- zh
- ja
- de
- es
- ko
- fr
- it
- pt
- nl
multilinguality: multilingual
tags:
- text-retrieval
- code-switching
task_categories:
- text-retrieval
task_ids:
- document-retrieval
---
<div align="center" style="padding: 40px 20px; background-color: white; border-radius: 12px; box-shadow: 0 2px 10px rgba(0, 0, 0, 0.05); max-width: 600px; margin: 0 auto;">
<h1 style="font-size: 3.5rem; color: #1a1a1a; margin: 0 0 20px 0; letter-spacing: 2px; font-weight: 700;">Touche2020-v3 CS-MTEB</h1>
<div style="font-size: 1.5rem; color: #4a4a4a; margin-bottom: 5px; font-weight: 300;">An <a href="https://github.com/embeddings-benchmark/mteb" style="color: #2c5282; font-weight: 600; text-decoration: none;">MTEB</a> dataset</div>
<div style="font-size: 0.9rem; color: #2c5282; margin-top: 10px;">Massive Text Embedding Benchmark</div>
</div>
Code-switching version of [mteb/webis-touche2020-v3](https://huggingface.co/datasets/mteb/webis-touche2020-v3), with queries rewritten in Chinese-English, Japanese-English, German-English, Spanish-English, Korean-English, French-English, Italian-English, Portuguese-English, Dutch-English code-switching styles.
## Dataset Structure
The dataset contains the following configurations:
**From original dataset (unchanged):**
- `corpus`: Original corpus documents
- `default`: Original relevance judgments (qrels)
**Code-switching queries:**
- `queries_zh_en`: Chinese-English code-switching queries
- `queries_ja_en`: Japanese-English code-switching queries
- `queries_de_en`: German-English code-switching queries
- `queries_es_en`: Spanish-English code-switching queries
- `queries_ko_en`: Korean-English code-switching queries
- `queries_fr_en`: French-English code-switching queries
- `queries_it_en`: Italian-English code-switching queries
- `queries_pt_en`: Portuguese-English code-switching queries
- `queries_nl_en`: Dutch-English code-switching queries
## Usage
```python
from datasets import load_dataset
# Load code-switching queries
queries_zh = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_zh_en")
queries_ja = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_ja_en")
queries_de = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_de_en")
queries_es = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_es_en")
queries_ko = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_ko_en")
queries_fr = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_fr_en")
queries_it = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_it_en")
queries_pt = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_pt_en")
queries_nl = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_nl_en")
# Load original configs
corpus = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "corpus")
qrels = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "default")
```
## Attribution
Based on [mteb/webis-touche2020-v3](https://huggingface.co/datasets/mteb/webis-touche2020-v3).
## Citation
If you use this dataset, please also cite the original:
```bibtex
@inproceedings{bondarenko2020overview,
author = {Alexander Bondarenko and Maik Fr\"{o}be and Meriem Beloucif and Lukas Gienapp and Yamen Ajjour and Alexander Panchenko and Chris Biemann and Benno Stein and Henning Wachsmuth and Martin Potthast and Matthias Hagen},
booktitle = {Experimental IR Meets Multilinguality, Multimodality, and Interaction. 11th International Conference of the CLEF Association (CLEF 2020)},
doi = {10.1007/978-3-030-58219-7\_26},
pages = {384--395},
title = {Overview of Touch\'{e} 2020: Argument Retrieval},
year = {2020},
}
@article{enevoldsen2025mmtebmassivemultilingualtext,
title={MMTEB: Massive Multilingual Text Embedding Benchmark},
author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and others},
journal={arXiv preprint arXiv:2502.13595},
year={2025},
url={https://arxiv.org/abs/2502.13595},
doi={10.48550/arXiv.2502.13595},
}
@article{muennighoff2022mteb,
author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Lo\"{\i}c and Reimers, Nils},
title = {MTEB: Massive Text Embedding Benchmark},
journal={arXiv preprint arXiv:2210.07316},
year = {2022},
url = {https://arxiv.org/abs/2210.07316},
doi = {10.48550/ARXIV.2210.07316},
}
```
配置项:
- 配置名称:corpus
数据文件:
- 路径:corpus/corpus-*
数据集划分:corpus
- 配置名称:default
数据文件:
- 数据集划分:test
路径:data/test-*
- 配置名称:queries_de_en
数据文件:
- 路径:queries_de_en/train-*
数据集划分:train
- 配置名称:queries_es_en
数据文件:
- 路径:queries_es_en/train-*
数据集划分:train
- 配置名称:queries_fr_en
数据文件:
- 路径:queries_fr_en/train-*
数据集划分:train
- 配置名称:queries_it_en
数据文件:
- 路径:queries_it_en/train-*
数据集划分:train
- 配置名称:queries_ja_en
数据文件:
- 路径:queries_ja_en/train-*
数据集划分:train
- 配置名称:queries_ko_en
数据文件:
- 路径:queries_ko_en/train-*
数据集划分:train
- 配置名称:queries_nl_en
数据文件:
- 路径:queries_nl_en/train-*
数据集划分:train
- 配置名称:queries_pt_en
数据文件:
- 路径:queries_pt_en/train-*
数据集划分:train
- 配置名称:queries_zh_en
数据文件:
- 路径:queries_zh_en/train-*
数据集划分:train
数据集信息:
- 配置名称:corpus
特征字段:
- 字段名:_id,数据类型:字符串(string)
- 字段名:title,数据类型:字符串(string)
- 字段名:text,数据类型:字符串(string)
数据集划分:
- 划分名称:corpus,样本数量:303732
- 配置名称:default
特征字段:
- 字段名:query-id,数据类型:字符串(string)
- 字段名:corpus-id,数据类型:字符串(string)
- 字段名:score,数据类型:64位浮点数(float64)
数据集划分:
- 划分名称:test,占用字节数:161729,样本数量:2849
下载大小:50929,数据集总大小:161729
- 配置名称:queries_de_en
特征字段:
- 字段名:_id,数据类型:字符串(string)
- 字段名:text,数据类型:字符串(string)
数据集划分:
- 划分名称:train,样本数量:49
- 配置名称:queries_es_en
特征字段:
- 字段名:_id,数据类型:字符串(string)
- 字段名:text,数据类型:字符串(string)
数据集划分:
- 划分名称:train,样本数量:49
- 配置名称:queries_fr_en
特征字段:
- 字段名:_id,数据类型:字符串(string)
- 字段名:text,数据类型:字符串(string)
数据集划分:
- 划分名称:train,样本数量:49
- 配置名称:queries_it_en
特征字段:
- 字段名:_id,数据类型:字符串(string)
- 字段名:text,数据类型:字符串(string)
数据集划分:
- 划分名称:train,样本数量:49
- 配置名称:queries_ja_en
特征字段:
- 字段名:_id,数据类型:字符串(string)
- 字段名:text,数据类型:字符串(string)
- 字段名:metadata,数据类型:结构体(struct),包含:
- 字段名:description,数据类型:字符串(string)
- 字段名:narrative,数据类型:字符串(string)
数据集划分:
- 划分名称:train,样本数量:49
- 配置名称:queries_ko_en
特征字段:
- 字段名:_id,数据类型:字符串(string)
- 字段名:text,数据类型:字符串(string)
数据集划分:
- 划分名称:train,样本数量:49
- 配置名称:queries_nl_en
特征字段:
- 字段名:_id,数据类型:字符串(string)
- 字段名:text,数据类型:字符串(string)
数据集划分:
- 划分名称:train,样本数量:49
- 配置名称:queries_pt_en
特征字段:
- 字段名:_id,数据类型:字符串(string)
- 字段名:text,数据类型:字符串(string)
数据集划分:
- 划分名称:train,样本数量:49
- 配置名称:queries_zh_en
特征字段:
- 字段名:_id,数据类型:字符串(string)
- 字段名:text,数据类型:字符串(string)
- 字段名:metadata,数据类型:结构体(struct),包含:
- 字段名:description,数据类型:字符串(string)
- 字段名:narrative,数据类型:字符串(string)
数据集划分:
- 划分名称:train,样本数量:49
许可证:MIT许可证(mit)
语言:英语、中文、日语、德语、西班牙语、韩语、法语、意大利语、葡萄牙语、荷兰语
多语言特性:多语言(multilingual)
标签:文本检索、语码转换(code-switching)
任务类别:文本检索
任务子任务:文档检索
<div align="center" style="padding: 40px 20px; background-color: white; border-radius: 12px; box-shadow: 0 2px 10px rgba(0, 0, 0, 0.05); max-width: 600px; margin: 0 auto;">
<h1 style="font-size: 3.5rem; color: #1a1a1a; margin: 0 0 20px 0; letter-spacing: 2px; font-weight: 700;">Touche2020-v3 CS-MTEB</h1>
<div style="font-size: 1.5rem; color: #4a4a4a; margin-bottom: 5px; font-weight: 300;">一款MTEB(Massive Text Embedding Benchmark,大规模文本嵌入基准)数据集</div>
<div style="font-size: 0.9rem; color: #2c5282; margin-top: 10px;">大规模文本嵌入基准</div>
</div>
本数据集为[mteb/webis-touche2020-v3](https://huggingface.co/datasets/mteb/webis-touche2020-v3)的语码转换(code-switching)版本,其查询语句采用汉英、日英、德英、西英、韩英、法英、意英、葡英、荷英的语码转换风格进行重写。
## 数据集结构
本数据集包含以下配置项:
**源自原始数据集(未作修改):**
- `corpus`:原始语料库(corpus)文档
- `default`:原始相关性判断(qrels)
**语码转换查询集:**
- `queries_zh_en`:汉英语码转换查询集
- `queries_ja_en`:日英语码转换查询集
- `queries_de_en`:德英语码转换查询集
- `queries_es_en`:西英语码转换查询集
- `queries_ko_en`:韩英语码转换查询集
- `queries_fr_en`:法英语码转换查询集
- `queries_it_en`:意英语码转换查询集
- `queries_pt_en`:葡英语码转换查询集
- `queries_nl_en`:荷英语码转换查询集
## 使用方法
python
from datasets import load_dataset
# 加载语码转换查询集
queries_zh = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_zh_en")
queries_ja = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_ja_en")
queries_de = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_de_en")
queries_es = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_es_en")
queries_ko = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_ko_en")
queries_fr = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_fr_en")
queries_it = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_it_en")
queries_pt = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_pt_en")
queries_nl = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "queries_nl_en")
# 加载原始配置
corpus = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "corpus")
qrels = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3_CS-MTEB", "default")
## 数据集归因
本数据集基于[mteb/webis-touche2020-v3](https://huggingface.co/datasets/mteb/webis-touche2020-v3)构建。
## 引用声明
若使用本数据集,请同时引用以下原始文献:
bibtex
@inproceedings{bondarenko2020overview,
author = {Alexander Bondarenko and Maik Fr"{o}be and Meriem Beloucif and Lukas Gienapp and Yamen Ajjour and Alexander Panchenko and Chris Biemann and Benno Stein and Henning Wachsmuth and Martin Potthast and Matthias Hagen},
booktitle = {Experimental IR Meets Multilinguality, Multimodality, and Interaction. 11th International Conference of the CLEF Association (CLEF 2020)},
doi = {10.1007/978-3-030-58219-7\_26},
pages = {384--395},
title = {Overview of Touch"{e} 2020: Argument Retrieval},
year = {2020},
}
@article{enevoldsen2025mmtebmassivemultilingualtext,
title={MMTEB: Massive Multilingual Text Embedding Benchmark},
author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and others},
journal={arXiv preprint arXiv:2502.13595},
year={2025},
url={https://arxiv.org/abs/2502.13595},
doi={10.48550/arXiv.2502.13595},
}
@article{muennighoff2022mteb,
author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Lo"{i}c and Reimers, Nils},
title = {MTEB: Massive Text Embedding Benchmark},
journal={arXiv preprint arXiv:2210.07316},
year = {2022},
url = {https://arxiv.org/abs/2210.07316},
doi = {10.48550/ARXIV.2210.07316},
}
提供机构:
UTokyo-Yokoya-Lab



