Sentiment-Aware Machine Translation for Indic Languages

Amulya Ratna Dash, Harpreet Singh Anand, Yashvardhan Sharma

2025

Abstract

Machine Translation (MT) is a critical application in the field of Natural Language Processing (NLP) that aims to translate text from one language to another language. Indic languages, characterized by their linguistic diversity, often encapsulate emotional and sentimental expressions that are difficult to map accurately when translated from English. In-order to bridge the gap in language barrier, text(reviews) in English should be translated to multiple languages while preserving the sentiment. In this paper, we focus on the machine translation of English into three low resource Indic languages by employing sentiment-aware in-context learning techniques with large language models. Our approach helps improve the average translation score by +4.74 absolute points.

Paper Citation

in Harvard Style

Dash A., Anand H. and Sharma Y. (2025). Sentiment-Aware Machine Translation for Indic Languages. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: EAA; ISBN 978-989-758-737-5, SciTePress, pages 948-953. DOI: 10.5220/0013404000003890

in Bibtex Style

@conference{eaa25,
author={Amulya Dash and Harpreet Anand and Yashvardhan Sharma},
title={Sentiment-Aware Machine Translation for Indic Languages},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: EAA},
year={2025},
pages={948-953},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013404000003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: EAA
TI - Sentiment-Aware Machine Translation for Indic Languages
SN - 978-989-758-737-5
AU - Dash A.
AU - Anand H.
AU - Sharma Y.
PY - 2025
SP - 948
EP - 953
DO - 10.5220/0013404000003890
PB - SciTePress