用多任务学习提升实体感知机器翻译效果
Enhancing Entity Aware Machine Translation with Multi-task Learning
- 联合训练实体识别与机器翻译两个任务
- 在SemEval 2025数据集上提升翻译准确率
- 适合需要精准翻译专有名词的场景
实体感知机器翻译（EAMT）因实体相关翻译数据稀缺且上下文处理复杂，成为自然语言处理中的难题。本文提出一种多任务学习方法，同时优化实体识别与机器翻译两个子任务，从而提升整体实体感知翻译性能。实验基于SemEval 2025竞赛任务2提供的数据集进行，结果表明该方法有效改善了翻译质量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。