mteb/CataloniaTweetClassification

Tasks

• text-classification

Citation text from the card

@inproceedings{zotova-etal-2020-multilingual,
  author = {Zotova, Elena  and
Agerri, Rodrigo  and
Nu{\~n}ez, Manuel  and
Rigau, German},
  booktitle = {Proceedings of the Twelfth Language Resources and Evaluation Conference},
  editor = {Calzolari, Nicoletta  and
B{\'e}chet, Fr{\'e}d{\'e}ric  and
Blache, Philippe  and
Choukri, Khalid  and
Cieri, Christopher  and
Declerck, Thierry  and
Goggi, Sara  and
Isahara, Hitoshi  and
Maegaard, Bente  and
Mariani, Joseph  and
Mazo, H{\'e}l{\`e}ne  and
Moreno, Asuncion  and
Odijk, Jan  and
Piperidis, Stelios},
  isbn = {979-10-95546-34-4},
  month = may,
  pages = {1368--1375},
  publisher = {European Language Resources Association},
  title = {Multilingual Stance Detection in Tweets: The {C}atalonia Independence Corpus},
  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 Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harr

All datasets marked Permissive or share-alike | JSON