# NLIP_Lab-IITH Low-Resource MT System for WMT24 Indic MT Shared Task

arXiv: https://arxiv.org/abs/2410.03215 · HTML: https://mlsanity.com/paper/2410.03215/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 4 Oct 2024.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [Balancing Training for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2004.06748/) (2020)
- [Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information](https://mlsanity.com/paper/2010.03142/) (2020)
- [Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2005.04816/) (2020)
- [Code-switching pre-training for neural machine translation](https://mlsanity.com/paper/2009.08088/) (2020)
- [Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languages](https://mlsanity.com/paper/2210.09644/) (2022)
- [Understanding and Mitigating the Uncertainty in Zero-Shot Translation](https://mlsanity.com/paper/2205.10068/) (2022)
- [Breaking Down Multilingual Machine Translation](https://mlsanity.com/paper/2110.08130/) (2021)

## Abstract (arXiv)

In this paper, we describe our system for the WMT 24 shared task of Low-Resource Indic Language Translation. We consider eng leftrightarrow as, kha, lus, mni as participating language pairs. In this shared task, we explore the finetuning of a pre-trained model motivated by the pre-trained objective of aligning embeddings closer by alignment augmentation citelin-etal-2020-pre for 22 scheduled Indian languages. Our primary system is based on language-specific finetuning on a pre-trained model. We achieve chrF2 scores of 50.6, 42.3, 54.9, and 66.3 on the official public test set for engrightarrowas, engrightarrowkha, engrightarrowlus, engrightarrowmni respectively. We also explore multilingual training with/without language grouping and layer-freezing. Our code, models, and generated translations are available here: https://github.com/pramitsahoo/WMT2024-LRILT.