MeBERT-Mixed
MeBERT-Mixed is a Marathi-English code-mixed BERT model trained on Roman + Devanagari text. It is a mBERT model fine-tuned on full L3Cube-MeCorpus. [dataset link] (https://github.com/l3cube-pune/MarathiNLP)
More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2306.14030)
Other models from MeBERT family: MeBERT MeRoBERTa
MeBERT-Mixed MeBERT-Mixed-v2 MeRoBERTa-Mixed
MeLID-RoBERTa MeHate-RoBERTa MeSent-RoBERTa MeHate-BERT MeLID-BERT
Citing:
@article{chavan2023my,
title={My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks},
author={Chavan, Tanmay and Gokhale, Omkar and Kane, Aditya and Patankar, Shantanu and Joshi, Raviraj},
journal={arXiv preprint arXiv:2306.14030},
year={2023}
}