Search papers, labs, and topics across Lattice.
Email:
2
0
4
This work proposes two approaches of code-mixed generation using parallel sentences of three languages and fine-tune contextual transformer-based models MuRIL and XLM-RoBERTa best suited for Indian languages for language identification in code-mixed settings.
Script-compatible language routing can unlock machine translation for unsupported classical languages like Prakrit, revealing new avenues for low-resource NLP.
