MTEB logo MTEB
semantic-similarity text

IN22GenBitextMining

Cite this task

@article{gala2023indictrans,
  author = {Jay Gala and Pranjal A Chitale and A K Raghavan and Varun Gumma and Sumanth Doddapaneni and Aswanth Kumar M and Janki Atul Nawale and Anupama Sujatha and Ratish Puduppully and Vivek Raghavan and Pratyush Kumar and Mitesh M Khapra and Raj Dabre and Anoop Kunchukuttan},
  issn = {2835-8856},
  journal = {Transactions on Machine Learning Research},
  note = {},
  title = {IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages},
  url = {https://openreview.net/forum?id=vfT4YuzAYA},
  year = {2023},
}

IN22-Gen is a n-way parallel general-purpose multi-domain benchmark dataset for machine translation spanning English and 22 Indic languages.

Domains: WebLegalGovernmentNewsReligiousNon-fictionWritten
Languages: AssameseBengaliBodo (India)Dogri (macrolanguage)EnglishGoan KonkaniGujaratiHindiKannadaKashmiriMaithiliMalayalamMarathiManipuriNepali (individual language)OdiaPanjabiSanskritSantaliSindhiTamilTeluguUrdu
Task type
BitextMining
Main metric
f1
License
cc-by-4.0
Dates
2022-10-01 → 2023-03-01
Annotations
expert-annotated
Sample creation
created
Models scored …
Dataset preview mteb/IN22GenBitextMining Open on HuggingFace →

Model scores

Loading…