marathi-topic-medium-doc

MahaNews-LPC-BERT

MahaNews-LPC-BERT is a MahaBERT(<a href="https://huggingface.co/l3cube-pune/marathi-bert-v2">l3cube-pune/marathi-bert-v2</a>) model fine-tuned on full L3Cube-MahaNews-LPC Corpus, a Marathi medium document / paragraph classification dataset. <br> It is a topic identification cum medium paragraph classification model with 12 output categories <br> [dataset link] (https://github.com/l3cube-pune/MarathiNLP)

More details on the dataset, models, and baseline results can be found in our [paper] (coming soon) <br> Citing:

@inproceedings{mittal2023l3cube,
  title={L3Cube-MahaNews: News-Based Short Text and Long Document Classification Datasets in Marathi},
  author={Mittal, Saloni and Magdum, Vidula and Hiwarkhedkar, Sharayu and Dhekane, Omkar and Joshi, Raviraj},
  booktitle={International Conference on Speech and Language Technologies for Low-resource Languages},
  pages={52--63},
  year={2023},
  organization={Springer}
}

Other Marathi Sentiment models from MahaNews family are shared here:<br>

<a href="https://huggingface.co/l3cube-pune/marathi-topic-long-doc"> MahaNews-LDC-BERT (long documents) </a> <br> <a href="https://huggingface.co/l3cube-pune/marathi-topic-short-doc"> MahaNews-SHC-BERT (short text) </a> <br> <a href="https://huggingface.co/l3cube-pune/marathi-topic-medium-doc"> MahaNews-LPC-BERT (medium paragraphs) </a> <br> <a href="https://huggingface.co/l3cube-pune/marathi-topic-all-doc"> MahaNews-All-BERT (all document lengths) </a> <br>