Howard University-AI4PC at SemEval-2025 Task 2: Improving Machine Translation With Context-Aware Entity-Only Pre-translations with GPT4o

Saurav Aryal, Jabez Agyemang - Prempeh


Abstract
This paper presents our work on a 3-Step GPT translation system developed for SemEval-2025 Task 2 to enhance the translation of named entities within machine translation. Our approach integrates (1) entity extraction via wikidata, (2) GPT-based refinement of entity translations, and (3) final context-aware GPT translation. Results from the original dataset of six languages show significant improvements in the handling of named entities compared to direct GPT-based translation baselines. We further discuss replicability, observed challenges, and outline future research directions.
Anthology ID:
2025.semeval-1.246
Volume:
Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
Month:
July
Year:
2025
Address:
Vienna, Austria
Editors:
Sara Rosenthal, Aiala Rosá, Debanjan Ghosh, Marcos Zampieri
Venues:
SemEval | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1885–1889
Language:
URL:
https://preview.aclanthology.org/transition-to-people-yaml/2025.semeval-1.246/
DOI:
Bibkey:
Cite (ACL):
Saurav Aryal and Jabez Agyemang - Prempeh. 2025. Howard University-AI4PC at SemEval-2025 Task 2: Improving Machine Translation With Context-Aware Entity-Only Pre-translations with GPT4o. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 1885–1889, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):
Howard University-AI4PC at SemEval-2025 Task 2: Improving Machine Translation With Context-Aware Entity-Only Pre-translations with GPT4o (Aryal & Agyemang - Prempeh, SemEval 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/transition-to-people-yaml/2025.semeval-1.246.pdf