多语言翻译中子词与跨语言迁移的系统性分析
A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation
AI总结：
本文系统分析子词分割方法对多语言翻译中跨语言迁移的影响，发现子词正则化促进多语言建模协同，BPE更利于跨语言微调，并揭示正字法词边界差异比语言不相关性更阻碍迁移。
摘要：
多语言建模可以通过共享的子词表示来改善低资源语言的机器翻译。本文研究了子词分割在跨语言迁移中的作用。我们系统地比较了几种子词方法在不同语言类型学中促进协同作用和防止干扰方面的有效性。我们的研究结果表明，子词正则化在多语言建模中增强了协同作用，而BPE在跨语言微调期间更有效地促进迁移。值得注意的是，我们的结果表明，正字法词边界惯例（书面词的形态粒度）的差异可能比语言不相关性更显著地阻碍跨语言迁移。我们的研究证实，围绕子词建模的决策可能是优化多语言建模收益的关键。
英文摘要：
Multilingual modelling can improve machine translation for low-resource languages, partly through shared subword representations. This paper studies the role of subword segmentation in cross-lingual transfer. We systematically compare the efficacy of several subword methods in promoting synergy and preventing interference across different linguistic typologies. Our findings show that subword regularisation boosts synergy in multilingual modelling, whereas BPE more effectively facilitates transfer during cross-lingual fine-tuning. Notably, our results suggest that differences in orthographic word boundary conventions (the morphological granularity of written words) may impede cross-lingual transfer more significantly than linguistic unrelatedness. Our study confirms that decisions around subword modelling can be key to optimising the benefits of multilingual modelling.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
