mteb/HindiDiscourseClassification

Tasks

• text-classification

Citation text from the card

@inproceedings{dhanwal-etal-2020-annotated,
  address = {Marseille, France},
  author = {Dhanwal, Swapnil  and
Dutta, Hritwik  and
Nankani, Hitesh  and
Shrivastava, Nilay  and
Kumar, Yaman  and
Li, Junyi Jessy  and
Mahata, Debanjan  and
Gosangi, Rakesh  and
Zhang, Haimin  and
Shah, Rajiv Ratn  and
Stent, Amanda},
  booktitle = {Proceedings of the 12th Language Resources and Evaluation Conference},
  isbn = {979-10-95546-34-4},
  language = {English},
  month = may,
  publisher = {European Language Resources Association},
  title = {An Annotated Dataset of Discourse Modes in {H}indi Stories},
  url = {https://www.aclweb.org/anthology/2020.lrec-1.149},
  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 Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and To

All datasets marked Permissive or share-alike | JSON