The first edition of Entity-Aware Ma-chine Translation (EA-MT), a new shared task whose goal is to track the progress and encourage the development of MT systems that can better handle the translation of text containing entities with names that are significantly different across languages. Given a sentence s in English containing an entity e, the task is to translate s into a target language while adapting the name of e to the target language to preserve the original meaning of the sentence.
Publication
Simone Conia, Min Li, Roberto Navigli, and Saloni Potdar. 2025. SemEval-2025 Task 2: Entity-Aware Machine Translation. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2535–2557, Vienna, Austria. Association for Computational Linguistics.
Language
Spanish
English
Arabic
Deuch
French
Italian
Korean
Chinese
URL Task
NLP topic
Dataset
Year
2025
Publication link
Ranking metric
Comet

