Rosetta at AlexandriaX-2026: 基于LoRA适配的NileChat用于上下文感知的阿拉伯语方言对话翻译
Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation
- Tanta University(坦塔大学)
- Alliance University(联盟大学)
- Robusta Studio(罗布斯塔工作室)
- Alexandria University(亚历山大大学)
- Yale University(耶鲁大学)
机构由 AI 辅助整理,请以论文原文为准。
AI总结:
本文介绍Rosetta系统,通过微调LoRA适配器于NileChat-3B,实现上下文感知的英语到阿拉伯语方言对话翻译,在共享任务中取得良好排名,并发现外部预训练可能导致负迁移。
AI中文摘要:
本文描述了Rosetta系统在AlexandriaX共享任务子任务1(上下文感知的英语到阿拉伯语方言对话翻译)中的表现,该系统参与了受限和非受限两个赛道。该方法在NileChat-3B上微调了一个LoRA适配器,使用结构化的系统/用户提示,根据方言和对话上下文调节生成。对于非受限赛道,适配器额外在MADAR和PADIC上进行了预训练。Rosetta在受限赛道中排名第4(spBLEU 26.10),在非受限赛道中排名第5(spBLEU 25.09)。实验结果表明,外部预训练仅对十三个方言中的两个有帮助,同时略微损害了整体性能,表明存在负迁移。
英文摘要:
This paper describes the Rosetta system for Subtask 1 (Context-Aware English-to-Dialectal Arabic Dialogue Translation) of the AlexandriaX shared task, participating in both constrained and unconstrained tracks. The approach fine-tunes a LoRA adapter on NileChat-3B using structured system/user prompts that condition generation on dialect and dialogue context. For the unconstrained track, the adapter is additionally pretrained on MADAR and PADIC. Rosetta ranked 4th in the constrained track (spBLEU 26.10) and 5th in the unconstrained track (spBLEU 25.09). The experimental results demonstrate that external pretraining helps only two of thirteen dialects while slightly hurting overall performance, suggesting negative transfer.