{
 "id": "mteb/NepaliNewsClassification",
 "owner": "mteb",
 "name": "NepaliNewsClassification",
 "downloads": 1617,
 "likes": 0,
 "last_modified": "2025-05-07T19:26:12.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{arora-2020-inltk,\n  abstract = {We present iNLTK, an open-source NLP library consisting of pre-trained language models and out-of-the-box support for Data Augmentation, Textual Similarity, Sentence Embeddings, Word Embeddings, Tokenization and Text Generation in 13 Indic Languages. By using pre-trained models from iNLTK for text classification on publicly available datasets, we significantly outperform previously reported results. On these datasets, we also show that by using pre-trained models and data augmentation from iNLTK, we can achieve more than 95{\\%} of the previous best performance by using less than 10{\\%} of the training data. iNLTK is already being widely used by the community and has 40,000+ downloads, 600+ stars and 100+ forks on GitHub.},\n  address = {Online},\n  author = {Arora, Gaurav},\n  booktitle = {Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)},\n  doi = {10.18653/v1/2020.nlposs-1.10},\n  editor = {Park, Eunjeong L.  and\nHagiwara, Masato  and\nMilajevs, Dmitrijs  and\nLiu, Nelson F.  and\nChauhan, Geeticka  and\nTan, Liling},\n  month = nov,\n  pages = {66--71},\n  publisher = {Association for Computational Linguistics},\n  title = {i{NLTK}: Natural Language Toolkit for Indic Languages},\n  url = {https://aclanthology.org/2020.nlposs-1.10},\n  year = {2020},\n}\n\n\n@article{enevoldsen2025mmtebmassivemultilingualtext,\n  title={MMTEB: Massive Multilingual Text Embedding Benchmark},\n  author={Kenneth Enevoldsen and Isaac Chung and Imen",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "517059b8db27c65544a855d90b3e30e5a9853fc3",
 "stated_evidence": "https://huggingface.co/datasets/mteb/NepaliNewsClassification/blob/517059b8db27c65544a855d90b3e30e5a9853fc3/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/NepaliNewsClassification/tree/517059b8db27c65544a855d90b3e30e5a9853fc3",
 "card_nc": false
}