AI 中文总结
该研究以五种突厥语为对象，利用成对迁移矩阵和mT5模型，发现紧密相关突厥语对间跨语言迁移更强，迁移方向及拉丁化对翻译指标有特定影响，迁移源在多数场景下稳定。
AI 中文摘要
跨语言迁移对低资源机器翻译至关重要，但其在紧密相关语族内的行为仍未得到充分表征。本研究针对土耳其语、阿塞拜疆语、乌兹别克语、哈萨克语、吉尔吉斯语五种突厥语，采用成对迁移矩阵开展研究，设置为每个模型以一个迁移源微调，在不同迁移目标上评估，翻译目标保持一致。通过mT5实验发现，紧密相关的突厥语对间迁移最强，尤其是土耳其语-阿塞拜疆语、哈萨克语-吉尔吉斯语；还表明迁移方向重要，同一迁移源-迁移目标对在翻译目标变化时表现不同。拉丁化在多种脚本不匹配场景下提升了BLEU和chrF分数，但效果在不同指标间不统一；额外分析显示，迁移源在不同数据集和模型设置下大多稳定。
英文摘要
Cross-lingual transfer is central to low-resource machine translation, but its behavior within closely related language families remains insufficiently characterized. We study transfer among five Turkic languages; Turkish, Azerbaijani, Uzbek, Kazakh, and Kyrgyz; using pairwise transfer matrices. In this setting, each model is fine-tuned with one transfer source and evaluated on a different transfer target while the translation target remains the same. Across mT5 experiments, we find that transfer is strongest between closely related Turkic pairs, especially Turkish-Azerbaijani and Kazakh-Kyrgyz. We also show that transfer direction matters, and that the same transfer source-transfer target pair can behave differently when the translation target changes. Latinization improves BLEU and chrF in several script-mismatched settings, but its effect is not uniform across metrics. Additional analyses show that transfer sources are mostly stable across different datasets and model settings.
