Hing Roberta Mixed

🚀 HingRoBERTa-Mixed

HingRoBERTa-Mixed is a Hindi-English code-mixed BERT model. It is trained on roman + devanagari text and fine-tuned from an xlm-RoBERTa model on the mixed script L3Cube-HingCorpus. This model offers a powerful solution for handling Hindi-English code-mixed text.

🚀 Quick Start

HingRoBERTa-Mixed is a valuable tool for tasks related to Hindi-English code-mixed text. It is based on the xlm-RoBERTa architecture and fine-tuned on the L3Cube-HingCorpus.

✨ Features

• Language Support: Supports Hindi, English, and multilingual code-mixed text.
• Training Data: Trained on the roman + devanagari text of the L3Cube-HingCorpus.
• Model Type: A fine-tuned xlm-RoBERTa model for code-mixed scenarios.

📚 Documentation

• Dataset Link: dataset link
• Paper: More details on the dataset, models, and baseline results can be found in our paper

📄 License

This project is licensed under the CC BY 4.0 license.

Other Models from HingBERT Family

• HingBERT
• HingMBERT
• HingBERT-Mixed
• HingBERT-Mixed-v2
• HingRoBERTa
• HingRoBERTa-Mixed
• HingGPT
• HingGPT-Devanagari
• HingBERT-LID

BibTeX Citation

@inproceedings{nayak-joshi-2022-l3cube,
    title = "{L}3{C}ube-{H}ing{C}orpus and {H}ing{BERT}: A Code Mixed {H}indi-{E}nglish Dataset and {BERT} Language Models",
    author = "Nayak, Ravindra  and Joshi, Raviraj",
    booktitle = "Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference",
    month = jun,
    year = "2022",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://aclanthology.org/2022.wildre-1.2",
    pages = "7--12",
}