Multitask Finetuning for Improving Neural Machine Translation in Indian Languages
This work addresses translation quality for Indian languages, but it is incremental as it builds on existing pretraining and finetuning techniques.
The paper tackles the problem of improving neural machine translation for Indian languages by proposing a multitask finetuning method that combines bilingual translation with causal language modeling, showing it could be better than standard finetuning across three language pairs.
Transformer based language models have led to impressive results across all domains in Natural Language Processing. Pretraining these models on language modeling tasks and finetuning them on downstream tasks such as Text Classification, Question Answering and Neural Machine Translation has consistently shown exemplary results. In this work, we propose a Multitask Finetuning methodology which combines the Bilingual Machine Translation task with an auxiliary Causal Language Modeling task to improve performance on the former task on Indian Languages. We conduct an empirical study on three language pairs, Marathi-Hindi, Marathi-English and Hindi-English, where we compare the multitask finetuning approach to the standard finetuning approach, for which we use the mBART50 model. Our study indicates that the multitask finetuning method could be a better technique than standard finetuning, and could improve Bilingual Machine Translation across language pairs.