对比微调与提示工程在实体感知翻译中的效果
HausaNLP at SemEval-2025 Task 2: Entity-Aware Fine-tuning vs. Prompt Engineering in Entity-Aware Machine Translation
- 比较实体感知微调与提示工程两种方法
- 在10种目标语言上验证了微调更优
- 适合关注实体翻译准确性的研究者
本文报告了我们在 SemEval 2025 第二项任务中的成果，该任务聚焦于实体感知机器翻译（EA-MT）。目标是开发能将英文句子准确翻译为目标语言的模型，尤其关注命名实体的处理。任务涵盖10种目标语言，以英语为源语言。我们介绍了所采用的不同系统，详细说明了实验结果，并讨论了关键发现。
原文摘要 · Abstract (English)
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.
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。