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

Pramit Sahoo, Maharaj Brahma, Maunendra Sankar Desarkar
10/4/2024
cs.CLcs.AI

Official code: pramitsahoo/WMT2024-LRILT (0 stars, MIT, last commit 2024-11-13).

Abstract

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 \cite{lin-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 eng$\rightarrow$as, eng$\rightarrow$kha, eng$\rightarrow$lus, eng$\rightarrow$mni 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.

View on arXivView PDF

Code Implementations(1)

pramitsahoo/WMT2024-LRILTOfficial100%
MIT
01Oct 3, 20241 years agoMIT

Similar Papers

NLIP_Lab-IITH Multilingual MT System for WAT24 MT Shared Task

91% match1 repo2024

Yes-MT's Submission to the Low-Resource Indic Language Translation Shared Task in WMT 2024

89% match2025

SPRING Lab IITM's submission to Low Resource Indic Language Translation Shared Task

89% match2024

Machine Translation Advancements of Low-Resource Indian Languages by Transfer Learning

85% match2024

Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Review

84% match2025

Adapting Multilingual LLMs to Low-Resource Languages using Continued Pre-training and Synthetic Corpus

83% match2024

Cite this paper

@article{sahoo2024nliplabiith,
  title  = {NLIP_Lab-IITH Low-Resource MT System for WMT24 Indic MT Shared Task},
  author = {Pramit Sahoo and Maharaj Brahma and Maunendra Sankar Desarkar},
  year   = {2024},
  eprint = {2410.03215},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.03215v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.03215.svg)](https://codeofpaper.com/paper/2410.03215)

Discussion