This paper presents our findings for SemEval 2025 Task 2, a shared task on entity-aware machine translation (EA-MT). The goal of this task is to develop translation models that can accurately translate English sentences into target languages, with a particular focus on handling named entities, which often pose challenges for MT systems. The task covers 10 target languages with English as the source. In this paper, we describe the different systems we employed, detail our results, and discuss insights gained from our experiments.
View on arXiv@article{abubakar2025_2503.19702,
title={ HausaNLP at SemEval-2025 Task 2: Entity-Aware Fine-tuning vs. Prompt Engineering in Entity-Aware Machine Translation },
author={ Abdulhamid Abubakar and Hamidatu Abdulkadir and Ibrahim Rabiu Abdullahi and Abubakar Auwal Khalid and Ahmad Mustapha Wali and Amina Aminu Umar and Maryam Bala and Sani Abdullahi Sani and Ibrahim Said Ahmad and Shamsuddeen Hassan Muhammad and Idris Abdulmumin and Vukosi Marivate },
journal={arXiv preprint arXiv:2503.19702},
year={ 2025 }
}