HausaNLP at SemEval-2025 Task 2: Entity-Aware Fine-tuning vs. Prompt Engineering in Entity-Aware Machine Translation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915213173850112 |
|---|---|
| author | Abubakar, Abdulhamid Abdulkadir, Hamidatu Abdullahi, Ibrahim Rabiu Khalid, Abubakar Auwal Wali, Ahmad Mustapha Umar, Amina Aminu Bala, Maryam Sani, Sani Abdullahi Ahmad, Ibrahim Said Muhammad, Shamsuddeen Hassan Abdulmumin, Idris Marivate, Vukosi |
| author_facet | Abubakar, Abdulhamid Abdulkadir, Hamidatu Abdullahi, Ibrahim Rabiu Khalid, Abubakar Auwal Wali, Ahmad Mustapha Umar, Amina Aminu Bala, Maryam Sani, Sani Abdullahi Ahmad, Ibrahim Said Muhammad, Shamsuddeen Hassan Abdulmumin, Idris Marivate, Vukosi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19702 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HausaNLP at SemEval-2025 Task 2: Entity-Aware Fine-tuning vs. Prompt Engineering in Entity-Aware Machine Translation Abubakar, Abdulhamid Abdulkadir, Hamidatu Abdullahi, Ibrahim Rabiu Khalid, Abubakar Auwal Wali, Ahmad Mustapha Umar, Amina Aminu Bala, Maryam Sani, Sani Abdullahi Ahmad, Ibrahim Said Muhammad, Shamsuddeen Hassan Abdulmumin, Idris Marivate, Vukosi Computation and Language 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. |
| title | HausaNLP at SemEval-2025 Task 2: Entity-Aware Fine-tuning vs. Prompt Engineering in Entity-Aware Machine Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.19702 |