mteb/FinParaSTS

Tasks

• sentence-similarity

Citation text from the card

@inproceedings{kanerva-etal-2021-finnish,
  address = {Reykjavik, Iceland (Online)},
  author = {Kanerva, Jenna  and
Ginter, Filip  and
Chang, Li-Hsin  and
Rastas, Iiro  and
Skantsi, Valtteri  and
Kilpel{\"a}inen, Jemina  and
Kupari, Hanna-Mari  and
Saarni, Jenna  and
Sev{\'o}n, Maija  and
Tarkka, Otto},
  booktitle = {Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)},
  editor = {Dobnik, Simon  and
{\\O}vrelid, Lilja},
  month = may # { 31--2 } # jun,
  pages = {288--298},
  publisher = {Link{\"o}ping University Electronic Press, Sweden},
  title = {{F}innish Paraphrase Corpus},
  url = {https://aclanthology.org/2021.nodalida-main.29},
  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 Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisse

All datasets marked Permissive or share-alike | JSON