# Multitask Finetuning for Improving Neural Machine Translation in Indian Languages

Source: [Multitask Finetuning for Improving Neural Machine Translation in Indian Languages](<https://www.sota2.com/research/paper/68fa6b631e209131cea2dfb9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:47:07.195Z

Authors: Shaily Desai, Atharva Kshirsagar, Manisha Marathe

Published: 2021-12-03T06:43:56.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2112.01742>)

[PDF](<https://arxiv.org/pdf/2112.01742.pdf>)
