UTokyo-Yokoya-Lab/webis-touche2020-v3-CSR-L

---
configs:
- config_name: corpus
data_files:
- path: corpus/corpus-*
split: corpus
- config_name: default
data_files:
- path: data/test-*
split: test
- config_name: queries_zh_en
data_files:
- path: queries_zh_en/train-*
split: train
- config_name: queries_ja_en
data_files:
- path: queries_ja_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_examples: 2849
- 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
- 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
language:
- eng
- zho
- jpn
multilinguality: multilingual
task_categories:
- text-retrieval
task_ids: []
tags:
- mteb
- text
- code-switching
---

<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-CodeSwitching</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 and Japanese-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 additions:**
- `queries_zh_en`: Chinese-English code-switching queries
- `queries_ja_en`: Japanese-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-codeswitching", "queries_zh_en")
queries_ja = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3-codeswitching", "queries_ja_en")

# Load original configs
corpus = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3-codeswitching", "corpus")
qrels = load_dataset("UTokyo-Yokoya-Lab/webis-touche2020-v3-codeswitching", "default")
```

## Attribution
Based on [mteb/webis-touche2020-v3](https://huggingface.co/datasets/mteb/webis-touche2020-v3) (MIT License).

## 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},
}
```