Enhancing Entity Aware Machine Translation with Multi-task Learning
This work addresses a specific challenge in natural language processing for translation tasks, but it appears incremental as it builds on existing multi-task learning approaches.
The paper tackles the problem of entity-aware machine translation by proposing a multi-task learning method that jointly optimizes named entity recognition and machine translation, resulting in improved performance on the SemEval 2025 Task 2 dataset.
Entity-aware machine translation (EAMT) is a complicated task in natural language processing due to not only the shortage of translation data related to the entities needed to translate but also the complexity in the context needed to process while translating those entities. In this paper, we propose a method that applies multi-task learning to optimize the performance of the two subtasks named entity recognition and machine translation, which improves the final performance of the Entity-aware machine translation task. The result and analysis are performed on the dataset provided by the organizer of Task 2 of the SemEval 2025 competition.