mteb/TNews

Tasks

• text-classification

Citation text from the card

@inproceedings{xu-etal-2020-clue,
  address = {Barcelona, Spain (Online)},
  author = {Xu, Liang  and
Hu, Hai and
Zhang, Xuanwei and
Li, Lu and
Cao, Chenjie and
Li, Yudong and
Xu, Yechen and
Sun, Kai and
Yu, Dian and
Yu, Cong and
Tian, Yin and
Dong, Qianqian and
Liu, Weitang and
Shi, Bo and
Cui, Yiming and
Li, Junyi and
Zeng, Jun and
Wang, Rongzhao and
Xie, Weijian and
Li, Yanting and
Patterson, Yina and
Tian, Zuoyu and
Zhang, Yiwen and
Zhou, He and
Liu, Shaoweihua and
Zhao, Zhe and
Zhao, Qipeng and
Yue, Cong and
Zhang, Xinrui and
Yang, Zhengliang and
Richardson, Kyle and
Lan, Zhenzhong },
  booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
  doi = {10.18653/v1/2020.coling-main.419},
  month = dec,
  pages = {4762--4772},
  publisher = {International Committee on Computational Linguistics},
  title = {{CLUE}: A {C}hinese Language Understanding Evaluation Benchmark},
  url = {https://aclanthology.org/2020.coling-main.419},
  year = {2020},
}


@article{enevoldsen2025mmtebmassivemultilingualtext,
  title={MMTEB: Massive Multilingual Text Embedding Benchmark},
  author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağata

All datasets marked Unclear | JSON