HausaNLP at SemEval-2025 Task 2: Entity-Aware Fine-tuning vs. Prompt Engineering in Entity-Aware Machine Translation
This work addresses entity translation issues in machine translation for multiple languages, but it is incremental as it compares existing fine-tuning and prompt engineering methods.
The paper tackled the challenge of accurately translating named entities in machine translation for 10 target languages, achieving competitive results in the SemEval 2025 Task 2 shared task.
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.