Telem Joyson Singh


2023

pdf
Can Big Models Help Diverse Languages? Investigating Large Pretrained Multilingual Models for Machine Translation of Indian Languages
Telem Joyson Singh | Sanasam Ranbir Singh | Priyankoo Sarmah
Proceedings of the 20th International Conference on Natural Language Processing (ICON)

Machine translation of Indian languages is challenging due to several factors, including linguistic diversity, limited parallel data, language divergence, and complex morphology. Recently, large pre-trained multilingual models have shown promise in improving translation quality. In this paper, we conduct a large-scale study on applying large pre-trained models for English-Indic machine translation through transfer learning across languages and domains. This study systematically evaluates the practical gains these models can provide and analyzes their capabilities for the translation of the Indian language by transfer learning. Specifically, we experiment with several models, including Meta’s mBART, mBART-manyto-many, NLLB-200, M2M-100, and Google’s MT5. These models are fine-tuned on small, high-quality English-Indic parallel data across languages and domains. Our findings show that adapting large pre-trained models to particular languages by fine-tuning improves translation quality across the Indic languages, even for languages unseen during pretraining. Domain adaptation through continued fine-tuning improves results. Our study provides insights into utilizing large pretrained models to address the distinct challenges of MT of Indian languages.

pdf
Subwords to Word Back Composition for Morphologically Rich Languages in Neural Machine Translation
Telem Joyson Singh | Sanasam Ranbir Singh | Priyankoo Sarmah
Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation