mteb/DanFeverRetrieval

Tasks

• text-retrieval

Citation text from the card

@inproceedings{norregaard-derczynski-2021-danfever,
  abstract = {We present a dataset, DanFEVER, intended for multilingual misinformation research. The dataset is in Danish and has the same format as the well-known English FEVER dataset. It can be used for testing methods in multilingual settings, as well as for creating models in production for the Danish language.},
  address = {Reykjavik, Iceland (Online)},
  author = {N{\o}rregaard, Jeppe  and
Derczynski, Leon},
  booktitle = {Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)},
  editor = {Dobnik, Simon  and
{\O}vrelid, Lilja},
  month = may # { 31--2 } # jun,
  pages = {422--428},
  publisher = {Link{\"o}ping University Electronic Press, Sweden},
  title = {{D}an{FEVER}: claim verification dataset for {D}anish},
  url = {https://aclanthology.org/2021.nodalida-main.47},
  year = {2021},
}


@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 Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Pośw

All datasets marked Permissive or share-alike | JSON